First Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e143a08ff1bd894b18035ba451190339cdc8c88c64c2574985a19cd354d580
-size 1766876
+oid sha256:7d97989779d002a79c814943ab90c8f4e4134225c74a2c082de24a04cb47f62e
+size 1768747

SoccerTwos/SoccerTwos-10000010.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d97989779d002a79c814943ab90c8f4e4134225c74a2c082de24a04cb47f62e
+size 1768747

SoccerTwos/SoccerTwos-10000010.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3562f614424ac49bdc17d15cd3ec67ced67c86ff97f078322907942238c2eb81
+size 28432146

SoccerTwos/SoccerTwos-8499995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d73361d913828d97ff14062a933c029feca6190e4287c94eb2e193118d55b5e
+size 1768747

SoccerTwos/SoccerTwos-8499995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af86511262b3daa270edb0767b0f6e3fc452f8ee31c96395ccac86af7069841c
+size 28432022

SoccerTwos/SoccerTwos-8999911.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09435f2ec5d5faf92db68bbbf762bd07613ea269c36f62f66d01b324ed8414dd
+size 1768747

SoccerTwos/SoccerTwos-8999911.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01c0fac979533317abac698e48f9f72b8cc1ac064278ba21e45a028b4a1014b
+size 28432022

SoccerTwos/SoccerTwos-9499853.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a76914ea70ea8c971aa6da07fa778b955ca1963513a0f90c328697ef68a2ad8
+size 1768747

SoccerTwos/SoccerTwos-9499853.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c8bfa2325a7fd6cd85708c6564ed9d09c84a079cf7dbad648f5b7ea68516e9
+size 28432022

SoccerTwos/SoccerTwos-9999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d97989779d002a79c814943ab90c8f4e4134225c74a2c082de24a04cb47f62e
+size 1768747

SoccerTwos/SoccerTwos-9999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b5e18d48adf6ae8603a6bbf325a55f865b1e4b73f10fde69ff804cc5ebdcaf
+size 28432022

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c239776c07d1c147899796bf9171e76c1521768171b5272ff7cd6afbaf4518f7
-size 9479714
+oid sha256:e5d6c246357956344d8c1e4684409f926471dcba7299eaa276ec760cd48c4398
+size 28431030

SoccerTwos/events.out.tfevents.1735412308.kaneUbuntu.78725.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0dab8b3ca4f6844bddf8256871c003bd1371a134b27d625ad79c3a72991e019
+size 411234

SoccerTwos/events.out.tfevents.1735412660.kaneUbuntu.79221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2c7976b7b96fb9a3cbdeddb555fd7482e2a707f82411f519853c9125457ddc
+size 9534197

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": 5000, "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.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "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": 10000000, "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.x86_64", "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

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 5000
+    max_steps: 10000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
@@ -74,8 +74,8 @@ checkpoint_settings:
   run_id: SoccerTwos
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -11,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.031 seconds
+- Completed reload, in  0.036 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: 0.346255 ms
+UnloadTime: 0.366135 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
@@ -47,12 +47,454 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 16 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]: 299 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 178552 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
@@ -97,12 +539,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 14]
+    [ALLOC_TEMP_Job.Worker 17]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 17]
+    [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -230,7 +672,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 13]
       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_EnlightenWorker] x 16
       Initial Block Size 64.0 KB
@@ -285,7 +727,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 1]
       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_Job.Worker 10]
       Initial Block Size 256.0 KB
@@ -302,12 +744,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 19]
+    [ALLOC_TEMP_Job.Worker 12]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 12]
+    [ALLOC_TEMP_Job.Worker 19]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -318,22 +760,22 @@ Memory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 2
+  Peak main deferred allocation count 3
     [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]: 300 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 178553 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.8 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]: 300 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 178553 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 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
@@ -362,13 +804,13 @@ 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]: 299 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 178552 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]: 300 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 178553 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -380,13 +822,13 @@ 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]: 300 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 178553 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]: 299 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 178552 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
@@ -398,13 +840,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 300 frames
+      Peak usage frame count: [0-1.0 KB]: 178553 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]: 299 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 178552 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

@@ -2,189 +2,261 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.295712471008301,
-            "min": 3.295712471008301,
-            "max": 3.295712471008301,
-            "count": 1
+            "value": 1.614660382270813,
+            "min": 1.5329911708831787,
+            "max": 3.1653454303741455,
+            "count": 946
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 105462.796875,
-            "min": 105462.796875,
-            "max": 105462.796875,
-            "count": 1
+            "value": 32654.890625,
+            "min": 6200.6533203125,
+            "max": 116047.109375,
+            "count": 946
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 817.3333333333334,
-            "min": 817.3333333333334,
-            "max": 817.3333333333334,
-            "count": 1
+            "value": 49.21212121212121,
+            "min": 41.33050847457627,
+            "max": 999.0,
+            "count": 946
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 29424.0,
-            "min": 29424.0,
-            "max": 29424.0,
-            "count": 1
+            "value": 19488.0,
+            "min": 3996.0,
+            "max": 31144.0,
+            "count": 946
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1198.7535925691843,
-            "min": 1198.7535925691843,
-            "max": 1198.7535925691843,
-            "count": 1
+            "value": 1590.3808205730516,
+            "min": 1210.6657767586505,
+            "max": 1619.790326024402,
+            "count": 941
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 4795.014370276737,
-            "min": 4795.014370276737,
-            "max": 4795.014370276737,
-            "count": 1
+            "value": 314895.4024734642,
+            "min": 2424.0827653708648,
+            "max": 377513.0365536685,
+            "count": 941
         },
         "SoccerTwos.Step.mean": {
-            "value": 9730.0,
-            "min": 9730.0,
-            "max": 9730.0,
-            "count": 1
+            "value": 9999992.0,
+            "min": 549657.0,
+            "max": 9999992.0,
+            "count": 946
         },
         "SoccerTwos.Step.sum": {
-            "value": 9730.0,
-            "min": 9730.0,
-            "max": 9730.0,
-            "count": 1
+            "value": 9999992.0,
+            "min": 549657.0,
+            "max": 9999992.0,
+            "count": 946
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.0035266962368041277,
-            "min": 0.0035266962368041277,
-            "max": 0.0035266962368041277,
-            "count": 1
+            "value": -0.07650735974311829,
+            "min": -0.11666654795408249,
+            "max": 0.21403224766254425,
+            "count": 946
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.045847050845623016,
-            "min": 0.045847050845623016,
-            "max": 0.045847050845623016,
-            "count": 1
+            "value": -15.22496509552002,
+            "min": -21.466644287109375,
+            "max": 29.588966369628906,
+            "count": 946
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.0035132351331412792,
-            "min": 0.0035132351331412792,
-            "max": 0.0035132351331412792,
-            "count": 1
+            "value": -0.07262206077575684,
+            "min": -0.12031123787164688,
+            "max": 0.2111627459526062,
+            "count": 946
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.04567205533385277,
-            "min": 0.04567205533385277,
-            "max": 0.04567205533385277,
-            "count": 1
+            "value": -14.451789855957031,
+            "min": -22.13726806640625,
+            "max": 29.504426956176758,
+            "count": 946
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 1
+            "count": 946
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 1
+            "count": 946
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.3076923076923077,
-            "min": -0.3076923076923077,
-            "max": -0.3076923076923077,
-            "count": 1
+            "value": -0.16366834197212105,
+            "min": -0.6058875005692244,
+            "max": 0.4048776696029219,
+            "count": 946
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -4.0,
-            "min": -4.0,
-            "max": -4.0,
-            "count": 1
+            "value": -32.57000005245209,
+            "min": -66.00479984283447,
+            "max": 55.14299935102463,
+            "count": 946
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.3076923076923077,
-            "min": -0.3076923076923077,
-            "max": -0.3076923076923077,
-            "count": 1
+            "value": -0.16366834197212105,
+            "min": -0.6058875005692244,
+            "max": 0.4048776696029219,
+            "count": 946
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -4.0,
-            "min": -4.0,
-            "max": -4.0,
-            "count": 1
+            "value": -32.57000005245209,
+            "min": -66.00479984283447,
+            "max": 55.14299935102463,
+            "count": 946
         },
         "SoccerTwos.IsTraining.mean": {
-            "value": 0.0,
-            "min": 0.0,
-            "max": 0.0,
-            "count": 1
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 946
         },
         "SoccerTwos.IsTraining.sum": {
-            "value": 0.0,
-            "min": 0.0,
-            "max": 0.0,
-            "count": 1
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 946
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015870315426339706,
+            "min": 0.00968948356846037,
+            "max": 0.0240408629955103,
+            "count": 456
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015870315426339706,
+            "min": 0.00968948356846037,
+            "max": 0.0240408629955103,
+            "count": 456
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10202294091383617,
+            "min": 0.00020218975963265013,
+            "max": 0.12481951639056206,
+            "count": 456
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10202294091383617,
+            "min": 0.00020218975963265013,
+            "max": 0.12481951639056206,
+            "count": 456
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10368427063028017,
+            "min": 0.00021083913209925717,
+            "max": 0.12807482952872912,
+            "count": 456
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10368427063028017,
+            "min": 0.00021083913209925717,
+            "max": 0.12807482952872912,
+            "count": 456
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 456
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 456
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 456
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 456
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 456
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 456
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1735411798",
+        "start_time_seconds": "1735412660",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/kane/miniconda3/envs/soccer_rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
+        "command_line_arguments": "/home/kane/miniconda3/envs/soccer_rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1735411807"
+        "end_time_seconds": "1735419135"
     },
-    "total": 9.324164813999232,
+    "total": 6475.497817641,
     "count": 1,
-    "self": 0.16678241299450747,
+    "self": 0.16737230699072825,
     "children": {
         "run_training.setup": {
-            "total": 0.009022557002026588,
+            "total": 0.010108270005730446,
             "count": 1,
-            "self": 0.009022557002026588
+            "self": 0.010108270005730446
         },
         "TrainerController.start_learning": {
-            "total": 9.148359844002698,
+            "total": 6475.320337064004,
             "count": 1,
-            "self": 0.007624238103744574,
+            "self": 5.83195191447885,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 0.7428388080006698,
-                    "count": 1,
-                    "self": 0.7428388080006698
+                    "total": 1.3394832180274534,
+                    "count": 49,
+                    "self": 1.3394832180274534
                 },
                 "TrainerController.advance": {
-                    "total": 8.34764483089748,
-                    "count": 1002,
-                    "self": 0.007876986979681533,
+                    "total": 6468.083171648497,
+                    "count": 651443,
+                    "self": 5.450060901894176,
                     "children": {
                         "env_step": {
-                            "total": 7.626386035924952,
-                            "count": 1002,
-                            "self": 5.608693927992135,
+                            "total": 4922.454020500554,
+                            "count": 651443,
+                            "self": 3595.986672016901,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 2.0129624889923434,
-                                    "count": 1002,
-                                    "self": 0.055025254005158786,
+                                    "total": 1322.9116125044602,
+                                    "count": 651443,
+                                    "self": 39.47856949702691,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1.9579372349871846,
-                                            "count": 2000,
-                                            "self": 1.9579372349871846
+                                            "total": 1283.4330430074333,
+                                            "count": 1190364,
+                                            "self": 1283.4330430074333
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.004729618940473301,
-                                    "count": 1002,
+                                    "total": 3.555735979192832,
+                                    "count": 651443,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 8.632488316987292,
-                                            "count": 1002,
+                                            "total": 6467.586811553083,
+                                            "count": 651443,
                                             "is_parallel": true,
-                                            "self": 4.1490815459656005,
+                                            "self": 3558.7149287097272,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -193,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.001034000000800006,
+                                                            "total": 0.0010675999947125092,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0002586410009826068,
+                                                            "self": 0.0002696989831747487,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0007753589998173993,
+                                                                    "total": 0.0007979010115377605,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007753589998173993
+                                                                    "self": 0.0007979010115377605
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.011528442002600059,
+                                                            "total": 0.011551907002285589,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00023984799918252975,
+                                                            "self": 0.00024401399423368275,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003896350026479922,
+                                                                    "total": 0.00021315100457286462,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003896350026479922
+                                                                    "self": 0.00021315100457286462
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.01021230900005321,
+                                                                    "total": 0.010420106002129614,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.01021230900005321
+                                                                    "self": 0.010420106002129614
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0006866500007163268,
+                                                                    "total": 0.0006746360013494268,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00013617199510918,
+                                                                    "self": 0.0001330439918092452,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005504780056071468,
+                                                                            "total": 0.0005415920095401816,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005504780056071468
+                                                                            "self": 0.0005415920095401816
                                                                         }
                                                                     }
                                                                 }
@@ -242,35 +314,49 @@
                                                         }
                                                     }
                                                 },
+                                                "steps_from_proto": {
+                                                    "total": 0.03312732799531659,
+                                                    "count": 96,
+                                                    "is_parallel": true,
+                                                    "self": 0.006399894969945308,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.026727433025371283,
+                                                            "count": 384,
+                                                            "is_parallel": true,
+                                                            "self": 0.026727433025371283
+                                                        }
+                                                    }
+                                                },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4.483406771021691,
-                                                    "count": 1001,
+                                                    "total": 2908.8387555153604,
+                                                    "count": 651442,
                                                     "is_parallel": true,
-                                                    "self": 0.2450781130537507,
+                                                    "self": 154.0329934919573,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.14917815698572667,
-                                                            "count": 1001,
+                                                            "total": 88.83800150844036,
+                                                            "count": 651442,
                                                             "is_parallel": true,
-                                                            "self": 0.14917815698572667
+                                                            "self": 88.83800150844036
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 3.4282893830168177,
-                                                            "count": 1001,
+                                                            "total": 2244.097924694048,
+                                                            "count": 651442,
                                                             "is_parallel": true,
-                                                            "self": 3.4282893830168177
+                                                            "self": 2244.097924694048
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.6608611179653963,
-                                                            "count": 2002,
+                                                            "total": 421.8698358209149,
+                                                            "count": 1302884,
                                                             "is_parallel": true,
-                                                            "self": 0.1195039621561591,
+                                                            "self": 78.01466316633741,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.5413571558092372,
-                                                                    "count": 8008,
+                                                                    "total": 343.8551726545775,
+                                                                    "count": 5211536,
                                                                     "is_parallel": true,
-                                                                    "self": 0.5413571558092372
+                                                                    "self": 343.8551726545775
                                                                 }
                                                             }
                                                         }
@@ -283,33 +369,52 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 0.713381807992846,
-                            "count": 1002,
-                            "self": 0.045957659916894045,
+                            "total": 1540.1790902460489,
+                            "count": 651443,
+                            "self": 50.01807652482239,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 0.667424148075952,
-                                    "count": 1002,
-                                    "self": 0.667424148075952
+                                    "total": 746.8638942911348,
+                                    "count": 651443,
+                                    "self": 745.5166783011227,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.347215990012046,
+                                            "count": 19,
+                                            "self": 1.347215990012046
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 743.2971194300917,
+                                    "count": 456,
+                                    "self": 464.1584625707692,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 279.1386568593225,
+                                            "count": 13695,
+                                            "self": 279.1386568593225
+                                        }
+                                    }
                                 }
                             }
                         }
                     }
                 },
                 "trainer_threads": {
-                    "total": 3.450004442129284e-07,
+                    "total": 4.0500162867829204e-07,
                     "count": 1,
-                    "self": 3.450004442129284e-07
+                    "self": 4.0500162867829204e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.05025162200035993,
+                    "total": 0.06572987799881957,
                     "count": 1,
-                    "self": 0.0005261660007818136,
+                    "self": 0.0008875089988578111,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.049725455999578116,
+                            "total": 0.06484236899996176,
                             "count": 1,
-                            "self": 0.049725455999578116
+                            "self": 0.06484236899996176
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,60 @@
 {
     "SoccerTwos": {
-        "elo": 1198.0086179957034,
         "checkpoints": [
             {
-                "steps": 14730,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14730.onnx",
+                "steps": 8499995,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499995.onnx",
                 "reward": 0.0,
-                "creation_time": 1735411807.2133741,
+                "creation_time": 1735418138.007778,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14730.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499995.pt"
+                ]
+            },
+            {
+                "steps": 8999911,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999911.onnx",
+                "reward": 0.0,
+                "creation_time": 1735418472.3267205,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999911.pt"
+                ]
+            },
+            {
+                "steps": 9499853,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499853.onnx",
+                "reward": 0.0,
+                "creation_time": 1735418798.4781756,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499853.pt"
+                ]
+            },
+            {
+                "steps": 9999992,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999992.onnx",
+                "reward": 0.0,
+                "creation_time": 1735419135.75325,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999992.pt"
+                ]
+            },
+            {
+                "steps": 10000010,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000010.onnx",
+                "reward": 0.0,
+                "creation_time": 1735419135.8224285,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000010.pt"
                 ]
             }
         ],
+        "elo": 1589.5484149337494,
         "final_checkpoint": {
-            "steps": 14730,
+            "steps": 10000010,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1735411807.2133741,
+            "creation_time": 1735419135.8224285,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-14730.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000010.pt"
             ]
         }
     },