5th Push

.gitattributes

@@ -102,3 +102,4 @@ SoccerTwos/SoccerTwos-499970.onnx.data filter=lfs diff=lfs merge=lfs -text
 SoccerTwos/SoccerTwos-4999976.onnx.data filter=lfs diff=lfs merge=lfs -text
 SoccerTwos/SoccerTwos-5000172.onnx.data filter=lfs diff=lfs merge=lfs -text
 SoccerTwos/SoccerTwos-999354.onnx.data filter=lfs diff=lfs merge=lfs -text
+SoccerTwos/SoccerTwos-10668.onnx.data filter=lfs diff=lfs merge=lfs -text

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311a97313c52758dd6ea2bfcb2a97bc99f37557eef8b82164af3dbdda09f1159
-size 65951
+oid sha256:b6397a0d8aa5748bdcf6073327e1a8062397c6334f23664798d1cc1ad733c578
+size 58065

SoccerTwos/SoccerTwos-10668.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6397a0d8aa5748bdcf6073327e1a8062397c6334f23664798d1cc1ad733c578
+size 58065

SoccerTwos/SoccerTwos-10668.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be7ccdf87efb89f71849f731fa4ea23ddbcd1ea1d3afd440d02cc83ce9c9e97
+size 1757184

SoccerTwos/SoccerTwos-10668.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04b5071c3842b8894d6d94a1eb24d19fecf36c1193033afac676cd3f9b53faa
+size 9480369

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:137ae14c5b770d871a47a8c8ae4bafbd10c0e6c6d53939798119afad8a7c2e0f
-size 126058521
+oid sha256:c7064e811ba55cc8b07557b283c89f84ff4fd7e6cdb66a59f132eb51f795bc34
+size 9480117

SoccerTwos/events.out.tfevents.1760977212.ada-B550-AORUS-ELITE.201423.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e52bc6f2a8916423482e0f476398745433eec48017971addbdabb38f1524435
+size 11278

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": 1024, "num_layers": 3, "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": 5000000, "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/SoccerTwos.app", "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": 10000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 2000, "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/SoccerTwos.app", "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}

configuration.yaml

@@ -16,8 +16,8 @@ behaviors:
     checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 1024
-      num_layers: 3
+      hidden_units: 512
+      num_layers: 2
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -37,13 +37,13 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 5000000
+    max_steps: 10000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
     self_play:
       save_steps: 50000
-      team_change: 200000
+      team_change: 2000
       swap_steps: 2000
       window: 10
       play_against_latest_model_ratio: 0.5

run_logs/Player-0.log

@@ -11,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.060 seconds
+- Completed reload, in  0.084 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)
@@ -36,7 +36,7 @@ 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: 0.772078 ms
+UnloadTime: 0.558057 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -47,685 +47,12 @@ 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
-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
-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 8 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]: 95159 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [2.0 KB-4.0 KB]: 1 frames, [8.0 KB-16.0 KB]: 584 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.1 MB
@@ -843,7 +170,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 9]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.7 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 13]
       Initial Block Size 32.0 KB
@@ -898,7 +225,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 12]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
@@ -911,22 +238,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 4
+  Peak main deferred allocation count 2
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 95160 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 586 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.9 MB
+      Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 95160 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 586 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -955,13 +282,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 95159 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 585 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]: 95160 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 586 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -973,13 +300,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 95160 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 586 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]: 95159 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 585 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.5 MB
@@ -991,13 +318,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 95160 frames
+      Peak usage frame count: [0-1.0 KB]: 586 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]: 95159 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 585 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

@@ -2,261 +2,189 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 1.9251084327697754,
-            "min": 1.9060689210891724,
-            "max": 3.2958130836486816,
-            "count": 500
+            "value": 3.2957422733306885,
+            "min": 3.2957422733306885,
+            "max": 3.2957422733306885,
+            "count": 1
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 41397.53125,
-            "min": 17920.822265625,
-            "max": 167205.515625,
-            "count": 500
+            "value": 205759.78125,
+            "min": 205759.78125,
+            "max": 205759.78125,
+            "count": 1
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 52.526315789473685,
-            "min": 45.7196261682243,
-            "max": 999.0,
-            "count": 500
+            "value": 295.3333333333333,
+            "min": 295.3333333333333,
+            "max": 295.3333333333333,
+            "count": 1
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19960.0,
-            "min": 13588.0,
-            "max": 27344.0,
-            "count": 500
+            "value": 21264.0,
+            "min": 21264.0,
+            "max": 21264.0,
+            "count": 1
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1486.9174419923545,
-            "min": 1181.9569568825848,
-            "max": 1506.4015408134596,
-            "count": 483
+            "value": 1197.3588306338852,
+            "min": 1197.3588306338852,
+            "max": 1197.3588306338852,
+            "count": 1
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 282514.31397854735,
-            "min": 2369.6371394464472,
-            "max": 319919.5209154878,
-            "count": 483
+            "value": 26341.894273945476,
+            "min": 26341.894273945476,
+            "max": 26341.894273945476,
+            "count": 1
         },
         "SoccerTwos.Step.mean": {
-            "value": 4999976.0,
-            "min": 9688.0,
-            "max": 4999976.0,
-            "count": 500
+            "value": 9998.0,
+            "min": 9998.0,
+            "max": 9998.0,
+            "count": 1
         },
         "SoccerTwos.Step.sum": {
-            "value": 4999976.0,
-            "min": 9688.0,
-            "max": 4999976.0,
-            "count": 500
+            "value": 9998.0,
+            "min": 9998.0,
+            "max": 9998.0,
+            "count": 1
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.03961816802620888,
-            "min": -0.18219952285289764,
-            "max": 0.16705821454524994,
-            "count": 500
+            "value": -0.07293880730867386,
+            "min": -0.07293880730867386,
+            "max": -0.07293880730867386,
+            "count": 1
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -7.4878339767456055,
-            "min": -15.550734519958496,
-            "max": 28.298982620239258,
-            "count": 500
+            "value": -2.47991943359375,
+            "min": -2.47991943359375,
+            "max": -2.47991943359375,
+            "count": 1
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.04478257894515991,
-            "min": -0.11971689015626907,
-            "max": 0.16362722218036652,
-            "count": 500
+            "value": -0.0728553980588913,
+            "min": -0.0728553980588913,
+            "max": -0.0728553980588913,
+            "count": 1
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -8.463907241821289,
-            "min": -16.90944480895996,
-            "max": 27.295597076416016,
-            "count": 500
+            "value": -2.477083444595337,
+            "min": -2.477083444595337,
+            "max": -2.477083444595337,
+            "count": 1
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 500
+            "count": 1
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 500
+            "count": 1
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.15585184980321815,
-            "min": -0.6666666666666666,
-            "max": 0.634120932152105,
-            "count": 500
+            "value": -0.38972941216300516,
+            "min": -0.38972941216300516,
+            "max": -0.38972941216300516,
+            "count": 1
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -29.455999612808228,
-            "min": -53.58680009841919,
-            "max": 59.07919955253601,
-            "count": 500
+            "value": -13.250800013542175,
+            "min": -13.250800013542175,
+            "max": -13.250800013542175,
+            "count": 1
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.15585184980321815,
-            "min": -0.6666666666666666,
-            "max": 0.634120932152105,
-            "count": 500
+            "value": -0.38972941216300516,
+            "min": -0.38972941216300516,
+            "max": -0.38972941216300516,
+            "count": 1
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -29.455999612808228,
-            "min": -53.58680009841919,
-            "max": 59.07919955253601,
-            "count": 500
+            "value": -13.250800013542175,
+            "min": -13.250800013542175,
+            "max": -13.250800013542175,
+            "count": 1
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 500
+            "count": 1
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 500
-        },
-        "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.017321076462152026,
-            "min": 0.011208989228665207,
-            "max": 0.024781595508102328,
-            "count": 239
-        },
-        "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.017321076462152026,
-            "min": 0.011208989228665207,
-            "max": 0.024781595508102328,
-            "count": 239
-        },
-        "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.09131397406260172,
-            "min": 1.0972371213332128e-05,
-            "max": 0.11502935116489728,
-            "count": 239
-        },
-        "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.09131397406260172,
-            "min": 1.0972371213332128e-05,
-            "max": 0.11502935116489728,
-            "count": 239
-        },
-        "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.09377672945459684,
-            "min": 1.3263954550287356e-05,
-            "max": 0.11784614870945613,
-            "count": 239
-        },
-        "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.09377672945459684,
-            "min": 1.3263954550287356e-05,
-            "max": 0.11784614870945613,
-            "count": 239
-        },
-        "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 239
-        },
-        "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 239
-        },
-        "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.20000000000000007,
-            "min": 0.20000000000000007,
-            "max": 0.20000000000000007,
-            "count": 239
-        },
-        "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.20000000000000007,
-            "min": 0.20000000000000007,
-            "max": 0.20000000000000007,
-            "count": 239
-        },
-        "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
-            "max": 0.005000000000000001,
-            "count": 239
-        },
-        "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
-            "max": 0.005000000000000001,
-            "count": 239
+            "count": 1
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1760939497",
+        "start_time_seconds": "1760977211",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/ada/work/ai/venv3.10/bin/mlagents-learn ./config/poca/SoccerTwosGo.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
+        "command_line_arguments": "/home/ada/work/ai/venv3.10/bin/mlagents-learn ./config/poca/SoccerTwos_tester.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.9.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1760947530"
+        "end_time_seconds": "1760977253"
     },
-    "total": 8032.405385018006,
+    "total": 41.61189289399772,
     "count": 1,
-    "self": 0.3195067480119178,
+    "self": 0.2689607540087309,
     "children": {
         "run_training.setup": {
-            "total": 0.020663704999606125,
+            "total": 0.021904640991124325,
             "count": 1,
-            "self": 0.020663704999606125
+            "self": 0.021904640991124325
         },
         "TrainerController.start_learning": {
-            "total": 8032.065214564995,
+            "total": 41.321027498997864,
             "count": 1,
-            "self": 6.379053071752423,
+            "self": 0.029680191568331793,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.259405160046299,
-                    "count": 25,
-                    "self": 3.259405160046299
+                    "total": 2.706091608008137,
+                    "count": 5,
+                    "self": 2.706091608008137
                 },
                 "TrainerController.advance": {
-                    "total": 8020.428702843201,
-                    "count": 337857,
-                    "self": 5.512063213274814,
+                    "total": 37.124809717424796,
+                    "count": 1962,
+                    "self": 0.02546850618091412,
                     "children": {
                         "env_step": {
-                            "total": 6374.960674629867,
-                            "count": 337857,
-                            "self": 4838.24769296679,
+                            "total": 36.01031182419683,
+                            "count": 1962,
+                            "self": 27.783992177515756,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1532.4690553792316,
-                                    "count": 337857,
-                                    "self": 31.79408094767132,
+                                    "total": 8.20694525410363,
+                                    "count": 1962,
+                                    "self": 0.13545427184726577,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1500.6749744315603,
-                                            "count": 634400,
-                                            "self": 1500.6749744315603
+                                            "total": 8.071490982256364,
+                                            "count": 3902,
+                                            "self": 8.071490982256364
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 4.243926283845212,
-                                    "count": 337857,
+                                    "total": 0.019374392577446997,
+                                    "count": 1962,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 8018.027773107882,
-                                            "count": 337857,
+                                            "total": 39.73117295120028,
+                                            "count": 1962,
                                             "is_parallel": true,
-                                            "self": 3912.221799851395,
+                                            "self": 15.547785302944249,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +193,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0031512249988736585,
+                                                            "total": 0.002536190004320815,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0007013610156718642,
+                                                            "self": 0.0005938320100540295,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0024498639832017943,
+                                                                    "total": 0.0019423579942667857,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0024498639832017943
+                                                                    "self": 0.0019423579942667857
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.021709003995056264,
+                                                            "total": 0.02080670598661527,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006267699936870486,
+                                                            "self": 0.00048261898336932063,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0006691689923172817,
+                                                                    "total": 0.0007062590011628345,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006691689923172817
+                                                                    "self": 0.0007062590011628345
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.01908179000020027,
+                                                                    "total": 0.018276557995704934,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.01908179000020027
+                                                                    "self": 0.018276557995704934
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0013312750088516623,
+                                                                    "total": 0.0013412700063781813,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002433550253044814,
+                                                                    "self": 0.00023606399190612137,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0010879199835471809,
+                                                                            "total": 0.00110520601447206,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0010879199835471809
+                                                                            "self": 0.00110520601447206
                                                                         }
                                                                     }
                                                                 }
@@ -315,50 +243,50 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4105.752160794465,
-                                                    "count": 337856,
+                                                    "total": 24.177161841245834,
+                                                    "count": 1961,
                                                     "is_parallel": true,
-                                                    "self": 246.46148524043383,
+                                                    "self": 1.5097127286862815,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 166.47152932237077,
-                                                            "count": 337856,
+                                                            "total": 1.050847560429247,
+                                                            "count": 1961,
                                                             "is_parallel": true,
-                                                            "self": 166.47152932237077
+                                                            "self": 1.050847560429247
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 3035.703743811173,
-                                                            "count": 337856,
+                                                            "total": 17.594837462034775,
+                                                            "count": 1961,
                                                             "is_parallel": true,
-                                                            "self": 3035.703743811173
+                                                            "self": 17.594837462034775
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 657.115402420488,
-                                                            "count": 675712,
+                                                            "total": 4.02176409009553,
+                                                            "count": 3922,
                                                             "is_parallel": true,
-                                                            "self": 107.85723203298403,
+                                                            "self": 0.6442178300058004,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 549.2581703875039,
-                                                                    "count": 2702848,
+                                                                    "total": 3.37754626008973,
+                                                                    "count": 15688,
                                                                     "is_parallel": true,
-                                                                    "self": 549.2581703875039
+                                                                    "self": 3.37754626008973
                                                                 }
                                                             }
                                                         }
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.05381246202159673,
-                                                    "count": 48,
+                                                    "total": 0.006225807010196149,
+                                                    "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 0.00842735696642194,
+                                                    "self": 0.0010096809855895117,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.04538510505517479,
-                                                            "count": 192,
+                                                            "total": 0.005216126024606638,
+                                                            "count": 24,
                                                             "is_parallel": true,
-                                                            "self": 0.04538510505517479
+                                                            "self": 0.005216126024606638
                                                         }
                                                     }
                                                 }
@@ -369,52 +297,33 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1639.9559650000592,
-                            "count": 337857,
-                            "self": 56.25888885749737,
+                            "total": 1.0890293870470487,
+                            "count": 1962,
+                            "self": 0.13861564101534896,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 665.5041086256824,
-                                    "count": 337857,
-                                    "self": 642.7210657846736,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 22.783042841008864,
-                                            "count": 10,
-                                            "self": 22.783042841008864
-                                        }
-                                    }
-                                },
-                                "_update_policy": {
-                                    "total": 918.1929675168794,
-                                    "count": 239,
-                                    "self": 515.6816689304833,
-                                    "children": {
-                                        "TorchPOCAOptimizer.update": {
-                                            "total": 402.51129858639615,
-                                            "count": 7170,
-                                            "self": 402.51129858639615
-                                        }
-                                    }
+                                    "total": 0.9504137460316997,
+                                    "count": 1962,
+                                    "self": 0.9504137460316997
                                 }
                             }
                         }
                     }
                 },
                 "trainer_threads": {
-                    "total": 6.310001481324434e-07,
+                    "total": 5.809997674077749e-07,
                     "count": 1,
-                    "self": 6.310001481324434e-07
+                    "self": 5.809997674077749e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 1.9980528589949245,
+                    "total": 1.4604454009968322,
                     "count": 1,
-                    "self": 0.0009465989860473201,
+                    "self": 0.0002542189904488623,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 1.9971062600088771,
+                            "total": 1.4601911820063833,
                             "count": 1,
-                            "self": 1.9971062600088771
+                            "self": 1.4601911820063833
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,60 +1,24 @@
 {
     "SoccerTwos": {
+        "elo": 1197.0215031921136,
         "checkpoints": [
             {
-                "steps": 3499996,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499996.onnx",
+                "steps": 10668,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10668.onnx",
                 "reward": 0.0,
-                "creation_time": 1760944916.6588755,
+                "creation_time": 1760977253.100307,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499996.pt"
-                ]
-            },
-            {
-                "steps": 3999948,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999948.onnx",
-                "reward": 0.0,
-                "creation_time": 1760945784.1763568,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999948.pt"
-                ]
-            },
-            {
-                "steps": 4499986,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499986.onnx",
-                "reward": 0.0,
-                "creation_time": 1760946659.641929,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4499986.pt"
-                ]
-            },
-            {
-                "steps": 4999976,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999976.onnx",
-                "reward": 0.0,
-                "creation_time": 1760947527.7321277,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999976.pt"
-                ]
-            },
-            {
-                "steps": 5000172,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5000172.onnx",
-                "reward": 0.0,
-                "creation_time": 1760947529.7431035,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5000172.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10668.pt"
                 ]
             }
         ],
-        "elo": 1482.721019978033,
         "final_checkpoint": {
-            "steps": 5000172,
+            "steps": 10668,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1760947529.7431035,
+            "creation_time": 1760977253.100307,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-5000172.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10668.pt"
             ]
         }
     },