Second Version

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c187d97ca2c574c1b1c52c7395958ce97c89fabe1563f324fd030eda5dcad2f5
+oid sha256:0f09efe7885f733207eba6c848d2bd9a861d76e33dc28eabb66b7d4940a5fba9
 size 1418184

Pyramids/{Pyramids-499962.onnx → Pyramids-1499970.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4955d63fef8e485be4d694d9a91cc3a3d93d9ef9b6bb5513500820cd2e75bd05
+oid sha256:655e07d7b953c06c325163981dcdb4466d7a7834c9b4d37c1f3bd7a8f15a5284
 size 1418184

Pyramids/{Pyramids-499962.pt → Pyramids-1499970.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98dd9ce86113d69a04ebb90e05955596fbab79f7bf91ccd4ff2ee102fe57e790
+oid sha256:230d667fc013a1b52ebbad09aaedb357129fa0e88134f6b6352e89f93f7b5f2b
 size 8650990

Pyramids/{Pyramids-999962.onnx → Pyramids-1999921.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28be9741abecae571027ff870caba24fbf700587ebcfbddf8afe86759049546c
+oid sha256:0f09efe7885f733207eba6c848d2bd9a861d76e33dc28eabb66b7d4940a5fba9
 size 1418184

Pyramids/{Pyramids-999962.pt → Pyramids-1999921.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8175d98d2bd35576195a3fc534f540833d9dde9f392785162313d5de1da5f31
+oid sha256:2d97b09c73fed30da0307e2d4c16bcc4fb84e212d4155ab0884a1743baadb88d
 size 8650990

Pyramids/Pyramids-2000049.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f09efe7885f733207eba6c848d2bd9a861d76e33dc28eabb66b7d4940a5fba9
+size 1418184

Pyramids/Pyramids-2000049.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62efc81a39994e50e20bb0a27b442236a7a4814050fefbad89661753bbab725
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea949f3cd12a6234cf3d7d73be6a56994ed6e66eb7fefdd3aea39a06a6189f2
+oid sha256:f62efc81a39994e50e20bb0a27b442236a7a4814050fefbad89661753bbab725
 size 8650990

Pyramids/events.out.tfevents.1679234463.e9217f9b1f10.81618.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cad120f07b09e5e7721edd64e8673d0b539aabcabf4d58056340cd4f38f0da
+size 1374

Pyramids/events.out.tfevents.1679234731.e9217f9b1f10.82800.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cac7bbf63a84970abbc8bf78ae6df0ddfe546dd7baefc1f644dd3e11707569e
+size 152455

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.1, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1400000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.1, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining2", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1400000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: PyramidsTraining2
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55243 [Flags] 2 [Guid] 961710937 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55494 [Flags] 2 [Guid] 1478970204 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.132 seconds
+- Completed reload, in  0.136 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,17 +65,15 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.163179 ms
+UnloadTime: 1.092283 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
-abort_threads: Failed aborting id: 0x7fbf72366700, mono_thread_manage will ignore it
-
 PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4067 frames, [32.0 KB-64.0 KB]: 16541 frames, [64.0 KB-128.0 KB]: 5659 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 881 frames, [32.0 KB-64.0 KB]: 6440 frames, [64.0 KB-128.0 KB]: 3945 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -130,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -206,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 25969 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 54 frames, [1.0 MB-2.0 MB]: 11213 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 13122
+  Peak main deferred allocation count 7516
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 26267 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 11266 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.9 MB
+      Peak Block count 2
+      Peak Allocated memory 23.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 26268 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 11267 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.2 MB
+      Peak Allocated memory 23.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26267 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 11266 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 26268 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 11267 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,39 +270,39 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 25969 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 59 frames, [1.0 MB-2.0 MB]: 11208 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26267 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 11266 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.3 MB
+      Peak Allocated memory 4.0 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26268 frames
+      Peak usage frame count: [0-1.0 KB]: 11267 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 26268 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 11267 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 26268 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 11267 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 28.6 KB
@@ -313,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679232788918,"processId":60875,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679236316278,"processId":82824,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.2454661726951599,
-            "min": 0.2438683658838272,
-            "max": 1.5889166593551636,
-            "count": 46
+            "value": 0.20909874141216278,
+            "min": 0.1949726790189743,
+            "max": 0.24659718573093414,
+            "count": 20
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 7391.4775390625,
-            "min": 7195.09228515625,
-            "max": 48201.375,
-            "count": 46
+            "value": 6363.29296875,
+            "min": 2694.81396484375,
+            "max": 7389.0244140625,
+            "count": 20
         },
         "Pyramids.Step.mean": {
-            "value": 1379901.0,
-            "min": 29910.0,
-            "max": 1379901.0,
-            "count": 46
+            "value": 1979953.0,
+            "min": 1409898.0,
+            "max": 1979953.0,
+            "count": 20
         },
         "Pyramids.Step.sum": {
-            "value": 1379901.0,
-            "min": 29910.0,
-            "max": 1379901.0,
-            "count": 46
+            "value": 1979953.0,
+            "min": 1409898.0,
+            "max": 1979953.0,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.6779295802116394,
-            "min": -0.09292546659708023,
-            "max": 0.7612824440002441,
-            "count": 46
+            "value": 0.7426161766052246,
+            "min": 0.6558880805969238,
+            "max": 0.8424283862113953,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 193.20993041992188,
-            "min": -22.395036697387695,
-            "max": 227.62344360351562,
-            "count": 46
+            "value": 225.0126953125,
+            "min": 61.653480529785156,
+            "max": 255.25579833984375,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.06917993724346161,
-            "min": -0.0011057952651754022,
-            "max": 0.3723164498806,
-            "count": 46
+            "value": 0.031264528632164,
+            "min": -0.05216704681515694,
+            "max": 0.03963925316929817,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 19.71628189086914,
-            "min": -0.2941415309906006,
-            "max": 88.23899841308594,
-            "count": 46
+            "value": 9.473152160644531,
+            "min": -6.927762985229492,
+            "max": 12.010693550109863,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 240.27777777777777,
+            "min": 223.68702290076337,
+            "max": 288.92727272727274,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30275.0,
+            "min": 9309.0,
+            "max": 31782.0,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7597222077468084,
+            "min": 1.6378581649877808,
+            "max": 1.7625564401668887,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 221.72499817609787,
+            "min": 66.69099980592728,
+            "max": 231.65419852733612,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7597222077468084,
+            "min": 1.6378581649877808,
+            "max": 1.7625564401668887,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 221.72499817609787,
+            "min": 66.69099980592728,
+            "max": 231.65419852733612,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.022153528766278806,
+            "min": 0.02162928428235598,
+            "max": 0.027806597438228147,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.7913446245511295,
+            "min": 0.9904941387940198,
+            "max": 3.175016888548271,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0715606110045753,
-            "min": 0.06373118343569027,
-            "max": 0.07409594399810193,
-            "count": 46
+            "value": 0.06888369233994228,
+            "min": 0.06337500430527142,
+            "max": 0.071930860919858,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.001848554064054,
-            "min": 0.4595870365823242,
-            "max": 1.0637401472389079,
-            "count": 46
+            "value": 1.0332553850991342,
+            "min": 0.25350001722108567,
+            "max": 1.0703795793096478,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015125273911204811,
-            "min": 0.0010844276371333522,
-            "max": 0.016129469255813295,
-            "count": 46
+            "value": 0.016365280428565006,
+            "min": 0.012337401918083735,
+            "max": 0.016365280428565006,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.21175383475686735,
-            "min": 0.010844276371333521,
-            "max": 0.24194203883719942,
-            "count": 46
+            "value": 0.24547920642847507,
+            "min": 0.0563335788998908,
+            "max": 0.24547920642847507,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.450995475551021e-06,
-            "min": 7.450995475551021e-06,
-            "max": 0.00029659622562438776,
-            "count": 46
+            "value": 5.23815825398e-06,
+            "min": 5.23815825398e-06,
+            "max": 8.919888276706249e-05,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0001043139366577143,
-            "min": 0.0001043139366577143,
-            "max": 0.0037952302777804277,
-            "count": 46
+            "value": 7.857237380970001e-05,
+            "min": 7.857237380970001e-05,
+            "max": 0.0012264580911809997,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1,
-            "min": 0.09999999999999998,
+            "value": 0.10000000000000002,
+            "min": 0.09999999999999999,
             "max": 0.10000000000000002,
-            "count": 46
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4000000000000001,
-            "min": 0.7,
+            "value": 1.5000000000000002,
+            "min": 0.39999999999999997,
             "max": 1.5000000000000002,
-            "count": 46
+            "count": 20
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002581149020408164,
-            "min": 0.0002581149020408164,
-            "max": 0.009886654275510205,
-            "count": 46
+            "value": 0.00018442739800000004,
+            "min": 0.00018442739800000004,
+            "max": 0.00298032045625,
+            "count": 20
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036136086285714296,
-            "min": 0.0036136086285714296,
-            "max": 0.12652116375714287,
-            "count": 46
+            "value": 0.0027664109700000004,
+            "min": 0.0027664109700000004,
+            "max": 0.040991018100000005,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.010419806465506554,
-            "min": 0.010419806465506554,
-            "max": 0.36617204546928406,
-            "count": 46
+            "value": 0.008875912055373192,
+            "min": 0.00887424685060978,
+            "max": 0.01034853607416153,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.14587728679180145,
-            "min": 0.14587728679180145,
-            "max": 2.563204288482666,
-            "count": 46
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 262.4824561403509,
-            "min": 242.04132231404958,
-            "max": 999.0,
-            "count": 46
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29923.0,
-            "min": 16581.0,
-            "max": 33378.0,
-            "count": 46
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7024122663495833,
-            "min": -0.999962551984936,
-            "max": 1.7566718604648486,
-            "count": 46
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 194.0749983638525,
-            "min": -31.998801663517952,
-            "max": 224.85399813950062,
-            "count": 46
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7024122663495833,
-            "min": -0.999962551984936,
-            "max": 1.7566718604648486,
-            "count": 46
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 194.0749983638525,
-            "min": -31.998801663517952,
-            "max": 224.85399813950062,
-            "count": 46
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.028350559796563812,
-            "min": 0.026500153520542837,
-            "max": 6.862230844357434,
-            "count": 46
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.2319638168082747,
-            "min": 3.1286544502800098,
-            "max": 116.65792435407639,
-            "count": 46
+            "value": 0.13313868641853333,
+            "min": 0.04139414429664612,
+            "max": 0.14527718722820282,
+            "count": 20
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 46
+            "count": 20
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 46
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679229482",
+        "start_time_seconds": "1679234727",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining2 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining2 --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679232788"
+        "end_time_seconds": "1679236316"
     },
-    "total": 3306.4794070059997,
+    "total": 1589.0462459160008,
     "count": 1,
-    "self": 0.8367734960011148,
+    "self": 0.9361756820035225,
     "children": {
         "run_training.setup": {
-            "total": 0.17392283699882682,
+            "total": 0.16557168299914338,
             "count": 1,
-            "self": 0.17392283699882682
+            "self": 0.16557168299914338
         },
         "TrainerController.start_learning": {
-            "total": 3305.468710673,
+            "total": 1587.944498550998,
             "count": 1,
-            "self": 2.3896251441310596,
+            "self": 1.0365882107980724,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 7.0244827779988555,
+                    "total": 7.150129449000815,
                     "count": 1,
-                    "self": 7.0244827779988555
+                    "self": 7.150129449000815
                 },
                 "TrainerController.advance": {
-                    "total": 3295.9087750568706,
-                    "count": 90145,
-                    "self": 2.4606926954766095,
+                    "total": 1579.6126246852,
+                    "count": 39434,
+                    "self": 1.1137139180646045,
                     "children": {
                         "env_step": {
-                            "total": 2407.1799921052516,
-                            "count": 90145,
-                            "self": 2236.1181065479086,
+                            "total": 1202.8060823790947,
+                            "count": 39434,
+                            "self": 1129.4289378840622,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 169.6538362672436,
-                                    "count": 90145,
-                                    "self": 7.15606690705863,
+                                    "total": 72.75138907831933,
+                                    "count": 39434,
+                                    "self": 3.1832067811119487,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 162.49776936018498,
-                                            "count": 87560,
-                                            "self": 162.49776936018498
+                                            "total": 69.56818229720739,
+                                            "count": 37556,
+                                            "self": 69.56818229720739
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.4080492900993704,
-                                    "count": 90145,
+                                    "total": 0.6257554167132184,
+                                    "count": 39434,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3297.432015708957,
-                                            "count": 90145,
+                                            "total": 1584.1774843564708,
+                                            "count": 39434,
                                             "is_parallel": true,
-                                            "self": 1241.269257969976,
+                                            "self": 533.6017628228074,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002846290999514167,
+                                                            "total": 0.0024970970007416327,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008743859980313573,
+                                                            "self": 0.0008042749977903441,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00197190500148281,
+                                                                    "total": 0.0016928220029512886,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00197190500148281
+                                                                    "self": 0.0016928220029512886
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05124855100075365,
+                                                            "total": 0.04806376800115686,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005672670013154857,
+                                                            "self": 0.0004168249979557004,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00048581000010017306,
+                                                                    "total": 0.0004748860010295175,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00048581000010017306
+                                                                    "self": 0.0004748860010295175
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.048365937000198755,
+                                                                    "total": 0.04548206400068011,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.048365937000198755
+                                                                    "self": 0.04548206400068011
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018295369991392363,
+                                                                    "total": 0.0016899930014915299,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040743300087342504,
+                                                                    "self": 0.0003765340043173637,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014221039982658112,
+                                                                            "total": 0.0013134589971741661,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014221039982658112
+                                                                            "self": 0.0013134589971741661
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2056.162757738981,
-                                                    "count": 90144,
+                                                    "total": 1050.5757215336635,
+                                                    "count": 39433,
                                                     "is_parallel": true,
-                                                    "self": 46.60205633400801,
+                                                    "self": 19.780520651271218,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 33.657413851666206,
-                                                            "count": 90144,
+                                                            "total": 13.942504169412132,
+                                                            "count": 39433,
                                                             "is_parallel": true,
-                                                            "self": 33.657413851666206
+                                                            "self": 13.942504169412132
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1838.478166507315,
-                                                            "count": 90144,
+                                                            "total": 958.0191729879116,
+                                                            "count": 39433,
                                                             "is_parallel": true,
-                                                            "self": 1838.478166507315
+                                                            "self": 958.0191729879116
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 137.42512104599155,
-                                                            "count": 90144,
+                                                            "total": 58.83352372506852,
+                                                            "count": 39433,
                                                             "is_parallel": true,
-                                                            "self": 30.324248896702557,
+                                                            "self": 13.165210859067884,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 107.10087214928899,
-                                                                    "count": 721152,
+                                                                    "total": 45.66831286600063,
+                                                                    "count": 315464,
                                                                     "is_parallel": true,
-                                                                    "self": 107.10087214928899
+                                                                    "self": 45.66831286600063
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 886.2680902561424,
-                            "count": 90145,
-                            "self": 4.6611480855317495,
+                            "total": 375.69282838804065,
+                            "count": 39434,
+                            "self": 2.0418972687511996,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 173.06847194963302,
-                                    "count": 90145,
-                                    "self": 172.8570300576357,
+                                    "total": 75.66356935731892,
+                                    "count": 39434,
+                                    "self": 75.40873285131966,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.21144189199731045,
+                                            "total": 0.2548365059992648,
                                             "count": 2,
-                                            "self": 0.21144189199731045
+                                            "self": 0.2548365059992648
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 708.5384702209776,
-                                    "count": 641,
-                                    "self": 447.93973490305325,
+                                    "total": 297.98736176197053,
+                                    "count": 284,
+                                    "self": 188.19357864699487,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 260.59873531792437,
-                                            "count": 31875,
-                                            "self": 260.59873531792437
+                                            "total": 109.79378311497567,
+                                            "count": 13665,
+                                            "self": 109.79378311497567
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.4360011846292764e-06,
+                    "total": 1.3930002751294523e-06,
                     "count": 1,
-                    "self": 1.4360011846292764e-06
+                    "self": 1.3930002751294523e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.14582625799812376,
+                    "total": 0.14515481299895328,
                     "count": 1,
-                    "self": 0.0019542619957064744,
+                    "self": 0.002944859996205196,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1438719960024173,
+                            "total": 0.14220995300274808,
                             "count": 1,
-                            "self": 0.1438719960024173
+                            "self": 0.14220995300274808
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499962,
-                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-499962.onnx",
-                "reward": 1.733999989926815,
-                "creation_time": 1679230541.8673005,
+                "steps": 1400039,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-1400039.onnx",
+                "reward": 1.7232857154948371,
+                "creation_time": 1679232788.1541061,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining2/Pyramids/Pyramids-499962.pt"
+                    "results/PyramidsTraining2/Pyramids/Pyramids-1400039.pt"
                 ]
             },
             {
-                "steps": 999962,
-                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-999962.onnx",
-                "reward": 1.7550000101327896,
-                "creation_time": 1679231760.9252436,
+                "steps": 1400039,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-1400039.onnx",
+                "reward": null,
+                "creation_time": 1679234467.2700083,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining2/Pyramids/Pyramids-999962.pt"
+                    "results/PyramidsTraining2/Pyramids/Pyramids-1400039.pt"
                 ]
             },
             {
-                "steps": 1400039,
-                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-1400039.onnx",
-                "reward": 1.7232857154948371,
-                "creation_time": 1679232788.1541061,
+                "steps": 1499970,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-1499970.onnx",
+                "reward": 1.7839999347925186,
+                "creation_time": 1679234999.3965633,
                 "auxillary_file_paths": [
-                    "results/PyramidsTraining2/Pyramids/Pyramids-1400039.pt"
+                    "results/PyramidsTraining2/Pyramids/Pyramids-1499970.pt"
+                ]
+            },
+            {
+                "steps": 1999921,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-1999921.onnx",
+                "reward": 1.5649999789893627,
+                "creation_time": 1679236315.2127757,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining2/Pyramids/Pyramids-1999921.pt"
+                ]
+            },
+            {
+                "steps": 2000049,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-2000049.onnx",
+                "reward": 1.5649999789893627,
+                "creation_time": 1679236315.3742762,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining2/Pyramids/Pyramids-2000049.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1400039,
+            "steps": 2000049,
             "file_path": "results/PyramidsTraining2/Pyramids.onnx",
-            "reward": 1.7232857154948371,
-            "creation_time": 1679232788.1541061,
+            "reward": 1.5649999789893627,
+            "creation_time": 1679236315.3742762,
             "auxillary_file_paths": [
-                "results/PyramidsTraining2/Pyramids/Pyramids-1400039.pt"
+                "results/PyramidsTraining2/Pyramids/Pyramids-2000049.pt"
             ]
         }
     },