Continued Training

README.md

@@ -1,35 +1,35 @@
----
-library_name: ml-agents
-tags:
-- SoccerTwos
-- deep-reinforcement-learning
-- reinforcement-learning
-- ML-Agents-SoccerTwos
----
-
-  # **poca** Agent playing **SoccerTwos**
-  This is a trained model of a **poca** agent playing **SoccerTwos**
-  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
-
-  ## Usage (with ML-Agents)
-  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
-
-  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
-  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
-  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
-  - A *longer tutorial* to understand how works ML-Agents:
-  https://huggingface.co/learn/deep-rl-course/unit5/introduction
-
-  ### Resume the training
-  ```bash
-  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
-  ```
-
-  ### Watch your Agent play
-  You can watch your agent **playing directly in your browser**
-
-  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
-  2. Step 1: Find your model_id: triksblade/poca-SoccerTwos
-  3. Step 2: Select your *.nn /*.onnx file
-  4. Click on Watch the agent play 👀
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: triksblade/poca-SoccerTwos
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
   

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d179e28a496f0bdb8e8c95a4ae7faa490e7dace79c8473fbfa09a8cbc03a1ad
+oid sha256:43a583bf9b768b1527bceaf6c7884ff8fc607dee6559683b61424884be28770a
 size 1768747

SoccerTwos/SoccerTwos-3499906.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ba156dc8726c53d580494e81fa1ae45b71d71c7d57fd3664619811dfbf34f5
+size 1768747

SoccerTwos/SoccerTwos-3499906.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31364e6ec59245e2465f9ed6918d98de6f7b055c0edb812952aba12567a6ab0
+size 28430358

SoccerTwos/SoccerTwos-3999859.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd83e2d097eb84b17ba8c0a856484bdb39f0b9271d8f31adebecff178a01304
+size 1768747

SoccerTwos/SoccerTwos-3999859.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ed477c0c33babff90b136efd7d15f99e618545343081f8666b4e7022b3e06d
+size 28430358

SoccerTwos/SoccerTwos-4499974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c693a625a52b0a203a87d261ef4cfda83a0c7d3779ccf073d67e4fc944c868b6
+size 1768747

SoccerTwos/SoccerTwos-4499974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd14b7327c7c1d85ced48d4e92dd56ab0061b3926221e3e265fb9ec1f86f1924
+size 28430358

SoccerTwos/SoccerTwos-4999972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143de6f8aa2494e97a505635d456bb327c1ecd853c1d54de199caed7d403aa4f
+size 1768747

SoccerTwos/SoccerTwos-4999972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1eecd5b4cab7e36856b31aa565cf6e0b4b7557229edec5a18f5569ddcb008c
+size 28430358

SoccerTwos/SoccerTwos-5144723.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a583bf9b768b1527bceaf6c7884ff8fc607dee6559683b61424884be28770a
+size 1768747

SoccerTwos/SoccerTwos-5144723.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5693d4e7b298823d70c3934a6f9f5c7ef840736d270aa38a578f19e085a8339b
+size 28430358

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f10aacc1d9f27faf23101be3285cf619bd5f61cf5c9bbfea4a4dd02e5cc008e
+oid sha256:a88303bb1d4f6513ec41de1dce53473f75860870b62c4a8557bdfc5b11b249c3
 size 28429366

SoccerTwos/events.out.tfevents.1716434628.SERVICE-MOBILE.15244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601d5287ac6967f5d3cbaf8bbe6188557ed49e954a29873525ff839522825e33
+size 1778267

SoccerTwos/events.out.tfevents.1716449422.SERVICE-MOBILE.5228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcecd5fa324686e7a4f0bf6a2dbb912ab2d650505dcf183d761fd16c99eed66
+size 175879

SoccerTwos/events.out.tfevents.1716455014.SERVICE-MOBILE.4032.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dacd19312956f90880f54997cee808c90b09dda0580e90db44ed0ec773da95d
+size 1758423

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/SoccerTwos.exe", "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": false, "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": 0.0003, "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/SoccerTwos.exe", "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -74,7 +74,7 @@ checkpoint_settings:
   run_id: SoccerTwos
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  9.119 seconds
+- Completed reload, in  8.918 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,266 +35,15 @@ 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: 1.308500 ms
+UnloadTime: 1.341700 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 4 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 29293 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 32145 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
@@ -317,12 +66,12 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 6]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -446,16 +195,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 29294 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 32146 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.0 MB
+      Peak Allocated memory 4.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 29294 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 32146 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -484,13 +233,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 29293 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 32145 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 29294 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 32146 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -502,16 +251,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 29294 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 32146 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 29293 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 32145 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 2.2 MB
+      Peak Allocated memory 2.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -520,13 +269,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 29294 frames
+      Peak usage frame count: [0-1.0 KB]: 32146 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]: 29293 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 32145 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,305 +2,305 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.60512113571167,
-            "min": 2.576058864593506,
-            "max": 3.2957584857940674,
-            "count": 153
+            "value": 1.9214180707931519,
+            "min": 1.862352967262268,
+            "max": 2.0375585556030273,
+            "count": 171
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 49768.234375,
-            "min": 19701.3984375,
-            "max": 105464.1875,
-            "count": 153
+            "value": 39473.61328125,
+            "min": 14372.5556640625,
+            "max": 44608.6640625,
+            "count": 171
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 70.44285714285714,
-            "min": 55.69318181818182,
-            "max": 999.0,
-            "count": 153
+            "value": 49.58585858585859,
+            "min": 40.706896551724135,
+            "max": 71.81428571428572,
+            "count": 171
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19724.0,
-            "min": 16380.0,
-            "max": 25536.0,
-            "count": 153
+            "value": 19636.0,
+            "min": 6180.0,
+            "max": 20260.0,
+            "count": 171
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1432.0507427110429,
-            "min": 1198.9900907842039,
-            "max": 1439.0801697786028,
-            "count": 152
+            "value": 1585.7677991109404,
+            "min": 1553.5179580138852,
+            "max": 1610.7972019352037,
+            "count": 171
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 200487.103979546,
-            "min": 2397.9801815684077,
-            "max": 245331.37821920833,
-            "count": 152
+            "value": 313982.0242239662,
+            "min": 94213.86956426132,
+            "max": 394536.63157583587,
+            "count": 171
         },
         "SoccerTwos.Step.mean": {
-            "value": 1529960.0,
-            "min": 9786.0,
-            "max": 1529960.0,
-            "count": 153
+            "value": 5139959.0,
+            "min": 3439951.0,
+            "max": 5139959.0,
+            "count": 171
         },
         "SoccerTwos.Step.sum": {
-            "value": 1529960.0,
-            "min": 9786.0,
-            "max": 1529960.0,
-            "count": 153
+            "value": 5139959.0,
+            "min": 3439951.0,
+            "max": 5139959.0,
+            "count": 171
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.08859968930482864,
-            "min": -0.03122873045504093,
-            "max": 0.25784891843795776,
-            "count": 153
+            "value": -0.060572218149900436,
+            "min": -0.08898256719112396,
+            "max": 0.1005156859755516,
+            "count": 171
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 12.315357208251953,
-            "min": -4.340793609619141,
-            "max": 26.724498748779297,
-            "count": 153
+            "value": -12.053871154785156,
+            "min": -17.240734100341797,
+            "max": 17.89179229736328,
+            "count": 171
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.07361045479774475,
-            "min": -0.03681948408484459,
-            "max": 0.25843432545661926,
-            "count": 153
+            "value": -0.05699760094285011,
+            "min": -0.087178535759449,
+            "max": 0.09999766200780869,
+            "count": 171
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 10.231853485107422,
-            "min": -5.117908477783203,
-            "max": 25.840808868408203,
-            "count": 153
+            "value": -11.342522621154785,
+            "min": -16.390785217285156,
+            "max": 17.799583435058594,
+            "count": 171
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 153
+            "count": 171
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 153
+            "count": 171
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.12326043329650549,
-            "min": -0.5714285714285714,
-            "max": 0.6532827560929046,
-            "count": 153
+            "value": -0.1673165817356589,
+            "min": -0.2861095484177671,
+            "max": 0.22272921378692884,
+            "count": 171
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 17.133200228214264,
-            "min": -21.79960000514984,
-            "max": 56.8355997800827,
-            "count": 153
+            "value": -33.29599976539612,
+            "min": -56.93580013513565,
+            "max": 39.645800054073334,
+            "count": 171
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.12326043329650549,
-            "min": -0.5714285714285714,
-            "max": 0.6532827560929046,
-            "count": 153
+            "value": -0.1673165817356589,
+            "min": -0.2861095484177671,
+            "max": 0.22272921378692884,
+            "count": 171
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 17.133200228214264,
-            "min": -21.79960000514984,
-            "max": 56.8355997800827,
-            "count": 153
+            "value": -33.29599976539612,
+            "min": -56.93580013513565,
+            "max": 39.645800054073334,
+            "count": 171
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 153
+            "count": 171
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 153
+            "count": 171
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.017969103282666765,
-            "min": 0.010487537668571653,
-            "max": 0.021603452736356606,
-            "count": 72
+            "value": 0.018759650674959025,
+            "min": 0.01115469560221148,
+            "max": 0.021448074255992346,
+            "count": 82
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.017969103282666765,
-            "min": 0.010487537668571653,
-            "max": 0.021603452736356606,
-            "count": 72
+            "value": 0.018759650674959025,
+            "min": 0.01115469560221148,
+            "max": 0.021448074255992346,
+            "count": 82
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08188363139828046,
-            "min": 0.0016951362524802486,
-            "max": 0.08501399084925651,
-            "count": 72
+            "value": 0.11596904620528221,
+            "min": 0.09423803612589836,
+            "max": 0.12632074877619742,
+            "count": 82
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08188363139828046,
-            "min": 0.0016951362524802486,
-            "max": 0.08501399084925651,
-            "count": 72
+            "value": 0.11596904620528221,
+            "min": 0.09423803612589836,
+            "max": 0.12632074877619742,
+            "count": 82
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.08477470974127452,
-            "min": 0.0017042422861171266,
-            "max": 0.08773589010039966,
-            "count": 72
+            "value": 0.11812345335880915,
+            "min": 0.0952321524421374,
+            "max": 0.12842872540156047,
+            "count": 82
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.08477470974127452,
-            "min": 0.0017042422861171266,
-            "max": 0.08773589010039966,
-            "count": 72
+            "value": 0.11812345335880915,
+            "min": 0.0952321524421374,
+            "max": 0.12842872540156047,
+            "count": 82
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 72
+            "count": 82
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 72
+            "count": 82
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 72
+            "count": 82
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 72
+            "count": 82
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 72
+            "count": 82
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 72
+            "count": 82
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1716284271",
+        "start_time_seconds": "1716454994",
         "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
-        "command_line_arguments": "\\\\?\\C:\\Users\\ASUSROG\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
+        "command_line_arguments": "\\\\?\\C:\\Users\\ASUSROG\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cpu",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1716295092"
+        "end_time_seconds": "1716467265"
     },
-    "total": 10820.996979999938,
+    "total": 12270.348834600001,
     "count": 1,
-    "self": 1.0817919998662546,
+    "self": 1.1021543000024394,
     "children": {
         "run_training.setup": {
-            "total": 0.2845190000953153,
+            "total": 0.3115802999996049,
             "count": 1,
-            "self": 0.2845190000953153
+            "self": 0.3115802999996049
         },
         "TrainerController.start_learning": {
-            "total": 10819.630668999976,
+            "total": 12268.935099999999,
             "count": 1,
-            "self": 7.065667584189214,
+            "self": 8.741336000073716,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 21.102362099918537,
-                    "count": 8,
-                    "self": 21.102362099918537
+                    "total": 24.339133400000264,
+                    "count": 10,
+                    "self": 24.339133400000264
                 },
                 "TrainerController.advance": {
-                    "total": 10791.088720715838,
-                    "count": 101527,
-                    "self": 7.374858103692532,
+                    "total": 12235.582564599925,
+                    "count": 119838,
+                    "self": 8.518548199779616,
                     "children": {
                         "env_step": {
-                            "total": 5743.239232376101,
-                            "count": 101527,
-                            "self": 4415.3459142574575,
+                            "total": 6489.675793600161,
+                            "count": 119838,
+                            "self": 5023.78484800052,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1323.189395701862,
-                                    "count": 101527,
-                                    "self": 43.19361850025598,
+                                    "total": 1460.3441352998884,
+                                    "count": 119838,
+                                    "self": 46.86335090045304,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1279.995777201606,
-                                            "count": 195294,
-                                            "self": 1279.995777201606
+                                            "total": 1413.4807843994354,
+                                            "count": 214308,
+                                            "self": 1413.4807843994354
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 4.703922416782007,
-                                    "count": 101527,
+                                    "total": 5.546810299753361,
+                                    "count": 119838,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 10749.106660613208,
-                                            "count": 101527,
+                                            "total": 12204.119910299984,
+                                            "count": 119838,
                                             "is_parallel": true,
-                                            "self": 7286.344790431438,
+                                            "self": 8252.098853600017,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.04099139990285039,
-                                                    "count": 16,
+                                                    "total": 0.0566629999966608,
+                                                    "count": 20,
                                                     "is_parallel": true,
-                                                    "self": 0.00800789927598089,
+                                                    "self": 0.011537199997746939,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0329835006268695,
-                                                            "count": 64,
+                                                            "total": 0.04512579999891386,
+                                                            "count": 80,
                                                             "is_parallel": true,
-                                                            "self": 0.0329835006268695
+                                                            "self": 0.04512579999891386
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 3462.720878781867,
-                                                    "count": 101527,
+                                                    "total": 3951.9643936999705,
+                                                    "count": 119838,
                                                     "is_parallel": true,
-                                                    "self": 200.90259891434107,
+                                                    "self": 227.40118399990342,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 198.3468875954859,
-                                                            "count": 101527,
+                                                            "total": 221.29594099971882,
+                                                            "count": 119838,
                                                             "is_parallel": true,
-                                                            "self": 198.3468875954859
+                                                            "self": 221.29594099971882
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2370.8362009989796,
-                                                            "count": 101527,
+                                                            "total": 2718.435361500345,
+                                                            "count": 119838,
                                                             "is_parallel": true,
-                                                            "self": 2370.8362009989796
+                                                            "self": 2718.435361500345
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 692.6351912730606,
-                                                            "count": 203054,
+                                                            "total": 784.8319072000031,
+                                                            "count": 239676,
                                                             "is_parallel": true,
-                                                            "self": 133.0821683453396,
+                                                            "self": 154.5026458000434,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 559.553022927721,
-                                                                    "count": 812216,
+                                                                    "total": 630.3292613999597,
+                                                                    "count": 958704,
                                                                     "is_parallel": true,
-                                                                    "self": 559.553022927721
+                                                                    "self": 630.3292613999597
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 5040.474630236044,
-                            "count": 101527,
-                            "self": 41.68894123204518,
+                            "total": 5737.388222799984,
+                            "count": 119838,
+                            "self": 47.69191030006823,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 1336.936692404328,
-                                    "count": 101527,
-                                    "self": 1335.9088755045086,
+                                    "total": 1710.6069001999222,
+                                    "count": 119838,
+                                    "self": 1709.2757095999232,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.0278168998192996,
-                                            "count": 3,
-                                            "self": 1.0278168998192996
+                                            "total": 1.3311905999989904,
+                                            "count": 4,
+                                            "self": 1.3311905999989904
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 3661.8489965996705,
-                                    "count": 73,
-                                    "self": 485.0931242010556,
+                                    "total": 3979.0894122999935,
+                                    "count": 83,
+                                    "self": 503.9244860999961,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 3176.755872398615,
-                                            "count": 2186,
-                                            "self": 3176.755872398615
+                                            "total": 3475.1649261999974,
+                                            "count": 2480,
+                                            "self": 3475.1649261999974
                                         }
                                     }
                                 }
@@ -346,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 3.100023604929447e-06,
+                    "total": 2.599999788799323e-06,
                     "count": 1,
-                    "self": 3.100023604929447e-06
+                    "self": 2.599999788799323e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.3739155000075698,
+                    "total": 0.2720633999997517,
                     "count": 1,
-                    "self": 0.016544800018891692,
+                    "self": 0.014902599999913946,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3573706999886781,
+                            "total": 0.25716079999983776,
                             "count": 1,
-                            "self": 0.3573706999886781
+                            "self": 0.25716079999983776
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,50 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 499442,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-499442.onnx",
+                "steps": 3499906,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499906.onnx",
                 "reward": 0.0,
-                "creation_time": 1716287975.3044803,
+                "creation_time": 1716455525.8830073,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-499442.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499906.pt"
                 ]
             },
             {
-                "steps": 999768,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-999768.onnx",
+                "steps": 3999859,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999859.onnx",
                 "reward": 0.0,
-                "creation_time": 1716291286.4634547,
+                "creation_time": 1716459059.8025615,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-999768.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999859.pt"
                 ]
             },
             {
-                "steps": 1499994,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1499994.onnx",
+                "steps": 4499974,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499974.onnx",
                 "reward": 0.0,
-                "creation_time": 1716294816.3197072,
+                "creation_time": 1716462597.8991349,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1499994.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499974.pt"
                 ]
             },
             {
-                "steps": 1534236,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1534236.onnx",
+                "steps": 4999972,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999972.onnx",
+                "reward": 0.0,
+                "creation_time": 1716466198.6816692,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999972.pt"
+                ]
+            },
+            {
+                "steps": 5144723,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5144723.onnx",
                 "reward": null,
-                "creation_time": 1716295091.7712605,
+                "creation_time": 1716467264.04394,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1534236.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5144723.pt"
                 ]
             }
         ],
-        "elo": 1431.976231608046,
+        "elo": 1585.1402033727863,
         "final_checkpoint": {
-            "steps": 1534236,
+            "steps": 5144723,
             "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
             "reward": null,
-            "creation_time": 1716295091.7712605,
+            "creation_time": 1716467264.04394,
             "auxillary_file_paths": [
-                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1534236.pt"
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5144723.pt"
             ]
         }
     },