Initial Commit

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00555090ea46a6a732fd93b87cdf86ecec6f7879058331028fb10f82e4b3dcba
+oid sha256:9008c991f7f146b32e9fa5652e032f5b9af8dff4b696afb71550f98b07f7004b
 size 1418184

Pyramids/{Pyramids-499898.onnx → Pyramids-1200097.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf943638f704b1b7acc1d51879d92ce1caa423d7564187fab046ebc561e131b
+oid sha256:9008c991f7f146b32e9fa5652e032f5b9af8dff4b696afb71550f98b07f7004b
 size 1418184

Pyramids/{Pyramids-499898.pt → Pyramids-1200097.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c13792e81d6b2877711cc47e9622a0f55433bef5edffce088659dbb653e9cef
+oid sha256:eae71f0eb945b483b4279335102c4e21cdc923bf3dbb034b3a41335746f5c03c
 size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f00e627a31a5e5258f4dc2fe7f5cc63a52d8be7ab8392579d0f2ffacd8bdd0d
+oid sha256:eae71f0eb945b483b4279335102c4e21cdc923bf3dbb034b3a41335746f5c03c
 size 8650990

Pyramids/events.out.tfevents.1682173592.55f8958bfe3e.16147.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc362fec75802d8d6ee9998dba2012c566152bfe2d7661c833e4ff5982d66f5
+size 1421

Pyramids/events.out.tfevents.1682173615.55f8958bfe3e.16307.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd503d3001bc6e9b9de6297ee9e0c2c2be042ba6dbc80e380b0c0f6db642929
+size 1421

Pyramids/events.out.tfevents.1682173650.55f8958bfe3e.16521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c601cc47a48a7d5cd6266e4fe85abdd11e7203274933b375bea3beec9f9297
+size 73917

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": 0.2, "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": 1000000, "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": "Pyramids Training", "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": 0.2, "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": 0.1, "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": 1200000, "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": "Pyramids Training", "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

@@ -37,7 +37,7 @@ behaviors:
           deterministic: false
       rnd:
         gamma: 0.99
-        strength: 0.01
+        strength: 0.1
         network_settings:
           normalize: false
           hidden_units: 64
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 1200000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 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] 55423 [Flags] 2 [Guid] 1346805214 [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] 55055 [Flags] 2 [Guid] 734562130 [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'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +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  0.098 seconds
+- Completed reload, in  0.107 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)
@@ -68,7 +65,7 @@ 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: 1.012614 ms
+UnloadTime: 1.004159 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.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 8535 frames, [32.0 KB-64.0 KB]: 8333 frames, [64.0 KB-128.0 KB]: 1898 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 109 frames, [32.0 KB-64.0 KB]: 2901 frames, [64.0 KB-128.0 KB]: 758 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
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       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 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +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]: 18468 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 139 frames, [1.0 MB-2.0 MB]: 3630 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 12451
+  Peak main deferred allocation count 7041
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 2 frames, [16.0 MB-32.0 MB]: 18765 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 3768 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 29.2 MB
+      Peak Block count 2
+      Peak Allocated memory 22.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18767 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 3769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.6 MB
+      Peak Allocated memory 22.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +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 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3768 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]: 18767 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 3769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 80 frames, [1.0 MB-2.0 MB]: 3689 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]: 18766 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 3768 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,27 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18767 frames
+      Peak usage frame count: [0-1.0 KB]: 3769 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]: 18767 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 3769 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]: 18767 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 3769 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1682172965787,"processId":2046,"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":1682174221572,"processId":16537,"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": 0.5019972920417786,
-            "min": 0.5019972920417786,
-            "max": 1.512757420539856,
-            "count": 33
+            "value": 0.4641489088535309,
+            "min": 0.4641489088535309,
+            "max": 0.5225774049758911,
+            "count": 7
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 14915.34375,
-            "min": 14915.34375,
-            "max": 45891.0078125,
-            "count": 33
+            "value": 14043.2890625,
+            "min": 10588.298828125,
+            "max": 15794.37890625,
+            "count": 7
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 460.21875,
+            "min": 460.21875,
+            "max": 539.9827586206897,
+            "count": 7
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29454.0,
+            "min": 15115.0,
+            "max": 31319.0,
+            "count": 7
         },
         "Pyramids.Step.mean": {
-            "value": 989973.0,
-            "min": 29952.0,
-            "max": 989973.0,
-            "count": 33
+            "value": 1199969.0,
+            "min": 1019974.0,
+            "max": 1199969.0,
+            "count": 7
         },
         "Pyramids.Step.sum": {
-            "value": 989973.0,
-            "min": 29952.0,
-            "max": 989973.0,
-            "count": 33
+            "value": 1199969.0,
+            "min": 1019974.0,
+            "max": 1199969.0,
+            "count": 7
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.2381294220685959,
-            "min": -0.11745283752679825,
-            "max": 0.2797795534133911,
-            "count": 33
+            "value": 0.36032506823539734,
+            "min": 0.2538290023803711,
+            "max": 0.36895352602005005,
+            "count": 7
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 61.67552185058594,
-            "min": -28.306133270263672,
-            "max": 72.05469512939453,
-            "count": 33
+            "value": 95.48614501953125,
+            "min": 42.13561248779297,
+            "max": 96.66582489013672,
+            "count": 7
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.13365747034549713,
-            "min": -0.012229234911501408,
-            "max": 0.42233166098594666,
-            "count": 33
+            "value": -0.6892226934432983,
+            "min": -0.6892226934432983,
+            "max": 0.8987314701080322,
+            "count": 7
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 34.617286682128906,
-            "min": -3.142913341522217,
-            "max": 100.09260559082031,
-            "count": 33
+            "value": -182.64401245117188,
+            "min": -182.64401245117188,
+            "max": 235.4676513671875,
+            "count": 7
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.3834874798776582,
+            "min": 1.253062042439806,
+            "max": 1.407818726496771,
+            "count": 7
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 88.54319871217012,
+            "min": 40.882999032735825,
+            "max": 90.10039849579334,
+            "count": 7
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.3834874798776582,
+            "min": 1.253062042439806,
+            "max": 1.407818726496771,
+            "count": 7
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 88.54319871217012,
+            "min": 40.882999032735825,
+            "max": 90.10039849579334,
+            "count": 7
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.6397047238133382,
+            "min": 0.6397047238133382,
+            "max": 0.7813150221171479,
+            "count": 7
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 40.941102324053645,
+            "min": 23.439450663514435,
+            "max": 43.4844670034945,
+            "count": 7
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06750206584304883,
-            "min": 0.06469694343877892,
-            "max": 0.071801862799885,
-            "count": 33
+            "value": 0.06577221771433307,
+            "min": 0.06530051335686862,
+            "max": 0.07252948782832844,
+            "count": 7
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9450289218026835,
-            "min": 0.49196683785285344,
-            "max": 1.0671819813033638,
-            "count": 33
+            "value": 0.920811048000663,
+            "min": 0.6442582946115231,
+            "max": 1.0879423174249265,
+            "count": 7
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015136220266781275,
-            "min": 6.519470551335432e-05,
-            "max": 0.015136220266781275,
-            "count": 33
+            "value": 0.10291241172013714,
+            "min": 0.02121116742439975,
+            "max": 0.10291241172013714,
+            "count": 7
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.21190708373493786,
-            "min": 0.0009127258771869604,
-            "max": 0.21190708373493786,
-            "count": 33
+            "value": 1.44077376408192,
+            "min": 0.19090050681959775,
+            "max": 1.44077376408192,
+            "count": 7
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.5671260490857094e-06,
-            "min": 7.5671260490857094e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 3.6392952155059478e-06,
+            "min": 3.6392952155059478e-06,
+            "max": 4.730763978637037e-05,
+            "count": 7
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010593976468719993,
-            "min": 0.00010593976468719993,
-            "max": 0.0035087597304134994,
-            "count": 33
+            "value": 5.095013301708327e-05,
+            "min": 5.095013301708327e-05,
+            "max": 0.0005762992079006666,
+            "count": 7
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10252234285714287,
-            "min": 0.10252234285714287,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10121306547619047,
+            "min": 0.10121306547619047,
+            "max": 0.1157691851851852,
+            "count": 7
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4353128000000002,
-            "min": 1.3886848,
-            "max": 2.5695865,
-            "count": 33
+            "value": 1.4169829166666665,
+            "min": 1.0419226666666668,
+            "max": 1.5920993333333333,
+            "count": 7
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026198205142857127,
-            "min": 0.00026198205142857127,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.00013118524107142842,
+            "min": 0.00013118524107142842,
+            "max": 0.0015853416,
+            "count": 7
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036677487199999977,
-            "min": 0.0036677487199999977,
-            "max": 0.11698169134999999,
-            "count": 33
+            "value": 0.001836593374999998,
+            "min": 0.001836593374999998,
+            "max": 0.0193307234,
+            "count": 7
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.01518812496215105,
-            "min": 0.01518812496215105,
-            "max": 0.4585326313972473,
-            "count": 33
+            "value": 0.013314624316990376,
+            "min": 0.012862170115113258,
+            "max": 0.01502944901585579,
+            "count": 7
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.21263374388217926,
-            "min": 0.21263374388217926,
-            "max": 3.209728479385376,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 628.8775510204082,
-            "min": 505.0833333333333,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30815.0,
-            "min": 15984.0,
-            "max": 32717.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.9635679590702056,
-            "min": -1.0000000521540642,
-            "max": 1.294859968746702,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 48.178397953510284,
-            "min": -31.994801700115204,
-            "max": 77.69159812480211,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.9635679590702056,
-            "min": -1.0000000521540642,
-            "max": 1.294859968746702,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 48.178397953510284,
-            "min": -31.994801700115204,
-            "max": 77.69159812480211,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.10053051478695124,
-            "min": 0.08307583548788292,
-            "max": 9.788902702741325,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 5.026525739347562,
-            "min": 4.577893010122352,
-            "max": 156.6224432438612,
-            "count": 33
+            "value": 0.1864047348499298,
+            "min": 0.1352650374174118,
+            "max": 0.2015685737133026,
+            "count": 7
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 7
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 7
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1682170330",
+        "start_time_seconds": "1682173649",
         "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=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1682172965"
+        "end_time_seconds": "1682174221"
     },
-    "total": 2635.004014771,
+    "total": 571.6703061529997,
     "count": 1,
-    "self": 0.5467032410001593,
+    "self": 0.9984784549992582,
     "children": {
         "run_training.setup": {
-            "total": 0.12831025599996337,
+            "total": 0.1252933630003099,
             "count": 1,
-            "self": 0.12831025599996337
+            "self": 0.1252933630003099
         },
         "TrainerController.start_learning": {
-            "total": 2634.329001274,
+            "total": 570.5465343350002,
             "count": 1,
-            "self": 2.095312731958984,
+            "self": 0.43370117899394245,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.607280360999994,
+                    "total": 4.351538560000336,
                     "count": 1,
-                    "self": 4.607280360999994
+                    "self": 4.351538560000336
                 },
                 "TrainerController.advance": {
-                    "total": 2627.519921878041,
-                    "count": 63290,
-                    "self": 2.3454810210701,
+                    "total": 565.5476142300072,
+                    "count": 12868,
+                    "self": 0.46691790904242225,
                     "children": {
                         "env_step": {
-                            "total": 1907.935517296987,
-                            "count": 63290,
-                            "self": 1758.620581698964,
+                            "total": 425.5422484500168,
+                            "count": 12868,
+                            "self": 395.82554607704105,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 148.03267836701065,
-                                    "count": 63290,
-                                    "self": 6.239593769027351,
+                                    "total": 29.452552143015055,
+                                    "count": 12868,
+                                    "self": 1.252491377041224,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 141.7930845979833,
-                                            "count": 62554,
-                                            "self": 141.7930845979833
+                                            "total": 28.20006076597383,
+                                            "count": 12563,
+                                            "self": 28.20006076597383
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.2822572310121245,
-                                    "count": 63290,
+                                    "total": 0.2641502299607055,
+                                    "count": 12868,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2627.1579005990075,
-                                            "count": 63290,
+                                            "total": 568.9347690650502,
+                                            "count": 12868,
                                             "is_parallel": true,
-                                            "self": 1020.6276869710412,
+                                            "self": 204.0601599120414,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005262920999996368,
+                                                            "total": 0.0020555050000439223,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003866537000021708,
+                                                            "self": 0.0006246969996936969,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013963839999746597,
+                                                                    "total": 0.0014308080003502255,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013963839999746597
+                                                                    "self": 0.0014308080003502255
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.08422994700003983,
+                                                            "total": 0.052971607000017684,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006147630000441495,
+                                                            "self": 0.0006087649994697131,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004426809999813486,
+                                                                    "total": 0.0005684940001629002,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004426809999813486
+                                                                    "self": 0.0005684940001629002
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08125897200000054,
+                                                                    "total": 0.04984381900021617,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08125897200000054
+                                                                    "self": 0.04984381900021617
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019135310000137906,
+                                                                    "total": 0.001950529000168899,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004100959999959741,
+                                                                    "self": 0.0004596290000336012,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015034350000178165,
+                                                                            "total": 0.0014909000001352979,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015034350000178165
+                                                                            "self": 0.0014909000001352979
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1606.5302136279663,
-                                                    "count": 63289,
+                                                    "total": 364.8746091530088,
+                                                    "count": 12867,
                                                     "is_parallel": true,
-                                                    "self": 42.074439737041075,
+                                                    "self": 8.189302013027827,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 27.746520481050595,
-                                                            "count": 63289,
+                                                            "total": 5.69794912699399,
+                                                            "count": 12867,
                                                             "is_parallel": true,
-                                                            "self": 27.746520481050595
+                                                            "self": 5.69794912699399
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1419.9460606999614,
-                                                            "count": 63289,
+                                                            "total": 327.05352850702275,
+                                                            "count": 12867,
                                                             "is_parallel": true,
-                                                            "self": 1419.9460606999614
+                                                            "self": 327.05352850702275
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 116.76319270991331,
-                                                            "count": 63289,
+                                                            "total": 23.93382950596424,
+                                                            "count": 12867,
                                                             "is_parallel": true,
-                                                            "self": 26.202783030956425,
+                                                            "self": 5.484773770170705,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 90.56040967895689,
-                                                                    "count": 506312,
+                                                                    "total": 18.449055735793536,
+                                                                    "count": 102936,
                                                                     "is_parallel": true,
-                                                                    "self": 90.56040967895689
+                                                                    "self": 18.449055735793536
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 717.2389235599838,
-                            "count": 63290,
-                            "self": 3.849056547948635,
+                            "total": 139.53844787094795,
+                            "count": 12868,
+                            "self": 0.8017819739684455,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 123.00701083003548,
-                                    "count": 63290,
-                                    "self": 122.72176271603519,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 0.2852481140002965,
-                                            "count": 2,
-                                            "self": 0.2852481140002965
-                                        }
-                                    }
+                                    "total": 24.607402939977874,
+                                    "count": 12868,
+                                    "self": 24.607402939977874
                                 },
                                 "_update_policy": {
-                                    "total": 590.3828561819997,
-                                    "count": 449,
-                                    "self": 376.116193068019,
+                                    "total": 114.12926295700163,
+                                    "count": 94,
+                                    "self": 72.6441576090192,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 214.2666631139807,
-                                            "count": 22770,
-                                            "self": 214.2666631139807
+                                            "total": 41.485105347982426,
+                                            "count": 4530,
+                                            "self": 41.485105347982426
                                         }
                                     }
                                 }
@@ -376,19 +369,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0630001270328648e-06,
+                    "total": 1.384999450237956e-06,
                     "count": 1,
-                    "self": 1.0630001270328648e-06
+                    "self": 1.384999450237956e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1064852399999836,
+                    "total": 0.21367898099924787,
                     "count": 1,
-                    "self": 0.0016666220003571652,
+                    "self": 0.004406408999784617,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10481861799962644,
+                            "total": 0.20927257199946325,
                             "count": 1,
-                            "self": 0.10481861799962644
+                            "self": 0.20927257199946325
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499898,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499898.onnx",
-                "reward": null,
-                "creation_time": 1682171572.3035755,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499898.pt"
-                ]
-            },
             {
                 "steps": 999965,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-999965.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000093.pt"
                 ]
+            },
+            {
+                "steps": 1000093,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000093.onnx",
+                "reward": null,
+                "creation_time": 1682173596.3184612,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000093.pt"
+                ]
+            },
+            {
+                "steps": 1000093,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000093.onnx",
+                "reward": null,
+                "creation_time": 1682173619.8688135,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000093.pt"
+                ]
+            },
+            {
+                "steps": 1200097,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1200097.onnx",
+                "reward": 1.710999995470047,
+                "creation_time": 1682174220.6124575,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1200097.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000093,
+            "steps": 1200097,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.5629999749362469,
-            "creation_time": 1682172965.29278,
+            "reward": 1.710999995470047,
+            "creation_time": 1682174220.6124575,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000093.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1200097.pt"
             ]
         }
     },