First Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1eb186de28179fa03a024979172224707f13315ff2da90b31f76fed959c76d4
+oid sha256:10612b6d5590e98eefde0c72ba31ef3796b72f4d37f867b2fb0732493421e769
 size 1768747

SoccerTwos/SoccerTwos-15821584.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10612b6d5590e98eefde0c72ba31ef3796b72f4d37f867b2fb0732493421e769
+size 1768747

SoccerTwos/SoccerTwos-15821584.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefb1510fb11f6a63f5b836ea7f87b2c9481658cc3534606276fd1fc5b5667d7
+size 28432146

SoccerTwos/SoccerTwos-26499762.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01878e0a9139c2ee4c9385e4ce5c953e48b12b45372c4e29e3743912cdd0e4d4
+size 1768747

SoccerTwos/SoccerTwos-26499762.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf8db9e3608d61bbdfed59a924541a1119f9fcbf5c5a237fe4e8d19edd8f5c5
+size 28432146

SoccerTwos/SoccerTwos-26999080.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513729bb22959ea84294e647ea4d537107d0a6f303cd3c0c784c3d2074cfa7a2
+size 1768747

SoccerTwos/SoccerTwos-26999080.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43d8ab632f87d4949f50bfb967ab0fa710eadcd7f34598a0a6751d05d035c17
+size 28432146

SoccerTwos/SoccerTwos-27499210.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3767dd617b8148fc18dc34aed15f1a16477459e84ecd8715de8a060249648bb7
+size 1768747

SoccerTwos/SoccerTwos-27499210.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256c17545c872848ded7e5603922745c5c176117f3367ffcbec0f6984f865520
+size 28432146

SoccerTwos/SoccerTwos-27999570.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65df49cb4effe8b7f8ca7de95547b2eaac063a34e7210e8ca89edd12bfd04ec7
+size 1768747

SoccerTwos/SoccerTwos-27999570.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de02787167c6972660d015d262a445bbdd2d948c6943b1173067b8033bc1b458
+size 28432146

SoccerTwos/SoccerTwos-28499570.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4aecb2a923fcb44f23c9e96b723c2281ed309d380fc3edba71e54f6a6e68fa
+size 1768747

SoccerTwos/SoccerTwos-28499570.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f3461f8b0ab40f6bd7387221351623849752dc2aaf0e1c5e0d066ee6b8343e
+size 28432146

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c59a77f62df2736f01dde58a4a57b16f8a07be5998b7df3977c771201552956c
+oid sha256:c241ccd3a53907e149b3ef0936d5ba37497de9580bfeac8c2980d7872b8f575c
 size 28431030

SoccerTwos/events.out.tfevents.1729541018.razer.284710.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1854e158f2477a42d1edfd9cdace00cb08c7e0e6bbd7252d7f2ee83587fbab
+size 1243

SoccerTwos/events.out.tfevents.1729541029.razer.285054.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dee241493df6756e99efa17bd87e82f7d857a0c962db5e184708087e10146b
+size 20827580

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "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}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.01, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "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}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 500000, "team_change": 2000000, "swap_steps": 20000, "window": 100, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0003
+      learning_rate: 0.01
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -42,10 +42,10 @@ behaviors:
     summary_freq: 10000
     threaded: false
     self_play:
-      save_steps: 50000
-      team_change: 200000
-      swap_steps: 2000
-      window: 10
+      save_steps: 500000
+      team_change: 2000000
+      swap_steps: 20000
+      window: 100
       play_against_latest_model_ratio: 0.5
       initial_elo: 1200.0
     behavioral_cloning: null

run_logs/timers.json

@@ -2,7 +2,7 @@
     "name": "root",
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1729520404",
+        "start_time_seconds": "1729541018",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/home/prefor/miniconda3/envs/rl_env/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos --run-id=SoccerTwos --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
@@ -10,31 +10,43 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.0+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1729520405"
+        "end_time_seconds": "1729541020"
     },
-    "total": 0.032795895000163,
+    "total": 2.123745284996403,
     "count": 1,
-    "self": 0.004454656002053525,
+    "self": 1.3168552280039876,
     "children": {
         "run_training.setup": {
-            "total": 0.025354117999086156,
+            "total": 0.01817727099842159,
             "count": 1,
-            "self": 0.025354117999086156
+            "self": 0.01817727099842159
         },
         "TrainerController.start_learning": {
-            "total": 0.0029871209990233183,
+            "total": 0.7887127859939937,
             "count": 1,
-            "self": 4.5368993596639484e-05,
+            "self": 0.0006044329929864034,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 0.002927527002611896,
+                    "total": 0.7849496830021963,
                     "count": 1,
-                    "self": 0.002927527002611896
+                    "self": 0.7849496830021963
+                },
+                "trainer_threads": {
+                    "total": 7.170019671320915e-07,
+                    "count": 1,
+                    "self": 7.170019671320915e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 1.4225002814782783e-05,
+                    "total": 0.00315795299684396,
                     "count": 1,
-                    "self": 1.4225002814782783e-05
+                    "self": 7.859300239942968e-05,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0030793599944445305,
+                            "count": 1,
+                            "self": 0.0030793599944445305
+                        }
+                    }
                 }
             }
         }

run_logs/training_status.json

@@ -1,4 +1,27 @@
 {
+    "SoccerTwos": {
+        "elo": 1200.0,
+        "checkpoints": [
+            {
+                "steps": 0,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-0.onnx",
+                "reward": null,
+                "creation_time": 1729541019.1616395,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-0.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 0,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1729541019.1616395,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-0.pt"
+            ]
+        }
+    },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.2.0.dev0",