First training for SoccerTwos

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb8822d9841470ccc328fe3861ee888a80db3d0ed26156d5c795817ed25e306
+oid sha256:5b3441da61bb8e5473e85462b25db9a356ac85911d2754d3218a5cb35d0fe686
 size 1768747

SoccerTwos/SoccerTwos-5499120.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063c3c35d4a7c7f90bf7ea2da4b3e2df2b7b48d1427fe76cb84c7c38b2310a17
+size 1768747

SoccerTwos/SoccerTwos-5499120.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acef8c12f87567257cb4bb0ea3233856b75420e6bd41abbb480d54eff29cefa7
+size 28432022

SoccerTwos/SoccerTwos-5999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb152633ded4f9d63e013633f953f0e061dcd8a80def69df87b9d9d292073da
+size 1768747

SoccerTwos/SoccerTwos-5999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28441fcfec84c439af0610b16ecdd7eaa1e6a579d788dd8d195d323cf852ebfa
+size 28432022

SoccerTwos/SoccerTwos-6499436.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8077171b5ee2bb3980f97ac41470f051e57cb22ec194a6e15f86c0ad6da93ddb
+size 1768747

SoccerTwos/SoccerTwos-6499436.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05343b13c490c4ad0dae20d68454dfd600ae646efad4e7aef1ea219eff7fc072
+size 28432022

SoccerTwos/SoccerTwos-6999326.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8261ea60197a064b0ea5b47965084dc05c79fdf863b897e39c63b85ac56d2212
+size 1768747

SoccerTwos/SoccerTwos-6999326.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5dcaa0ead57d9eace52279c90d01b1f2c93a9b9088aea60d261cad165a51ccf
+size 28432022

SoccerTwos/SoccerTwos-7425648.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3441da61bb8e5473e85462b25db9a356ac85911d2754d3218a5cb35d0fe686
+size 1768747

SoccerTwos/SoccerTwos-7425648.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2adab898659463169b549a744ee497cb40dfc6122073513a45360541fb07a9
+size 28432022

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdffe9c3fc53c6a77ba4b73d0aa842f3a6053c32c9898b7e7106b6c8117f037
+oid sha256:c6b421e0c27541e9d7abe842e23eee5553e613e9b5d27aa7995cf7ef1ec8101b
 size 28431030

SoccerTwos/events.out.tfevents.1724497817.Montana.18599.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abeec0d0f5519b0b67a6ebd05bd28c1f82b9e0b0b244689313d8182f6f03546b
+size 1311959

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": 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.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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SoccerTwos/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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos1", "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: 5000000
+    max_steps: 50000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -11,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.149 seconds
+- Completed reload, in  0.123 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: 1.617522 ms
+UnloadTime: 0.473460 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
@@ -1119,453 +1119,12 @@ 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
 Setting up 4 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 65046 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 46880 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
@@ -1623,7 +1182,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 4]
       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 3]
       Initial Block Size 256.0 KB
@@ -1678,7 +1237,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 1]
       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_Job.Worker 2]
       Initial Block Size 256.0 KB
@@ -1717,13 +1276,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 65047 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 46881 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.7 MB
+      Peak Allocated memory 4.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 65047 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 46881 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.5 MB
@@ -1755,13 +1314,13 @@ 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]: 65046 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 46880 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]: 65047 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 46881 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -1773,16 +1332,16 @@ 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]: 65047 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 46881 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]: 65046 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 46880 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -1791,13 +1350,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 65047 frames
+      Peak usage frame count: [0-1.0 KB]: 46881 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]: 65046 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 46880 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

@@ -2,201 +2,201 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.1992390155792236,
-            "min": 3.1031758785247803,
-            "max": 3.218050479888916,
-            "count": 336
+            "value": 3.127368927001953,
+            "min": 3.0976717472076416,
+            "max": 3.189692735671997,
+            "count": 242
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 46990.421875,
-            "min": 6413.4365234375,
-            "max": 122198.5703125,
-            "count": 336
+            "value": 100075.8046875,
+            "min": 15248.029296875,
+            "max": 130752.9921875,
+            "count": 242
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 748.5714285714286,
-            "min": 419.1818181818182,
+            "value": 602.75,
+            "min": 428.6,
             "max": 999.0,
-            "count": 336
+            "count": 242
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 20960.0,
-            "min": 10296.0,
-            "max": 28920.0,
-            "count": 336
+            "value": 19288.0,
+            "min": 12792.0,
+            "max": 27500.0,
+            "count": 242
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1187.4790280937716,
-            "min": 1181.964705856489,
-            "max": 1212.187109219361,
-            "count": 226
+            "value": 1206.8610828455319,
+            "min": 1186.7395702703918,
+            "max": 1212.688940503701,
+            "count": 171
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 9499.832224750173,
-            "min": 2365.805192585449,
-            "max": 12111.580319211516,
-            "count": 226
+            "value": 2413.7221656910638,
+            "min": 2374.981983800177,
+            "max": 14285.838900584944,
+            "count": 171
         },
         "SoccerTwos.Step.mean": {
-            "value": 4999694.0,
-            "min": 1649257.0,
-            "max": 4999694.0,
-            "count": 336
+            "value": 7419648.0,
+            "min": 5009269.0,
+            "max": 7419648.0,
+            "count": 242
         },
         "SoccerTwos.Step.sum": {
-            "value": 4999694.0,
-            "min": 1649257.0,
-            "max": 4999694.0,
-            "count": 336
+            "value": 7419648.0,
+            "min": 5009269.0,
+            "max": 7419648.0,
+            "count": 242
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.00022763109882362187,
-            "min": -0.01638786494731903,
-            "max": 0.007851633243262768,
-            "count": 336
+            "value": -0.0008507742313668132,
+            "min": -0.023815060034394264,
+            "max": 0.007759155239909887,
+            "count": 242
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.003186835441738367,
-            "min": -0.20262610912322998,
-            "max": 0.14132939279079437,
-            "count": 336
+            "value": -0.013612387701869011,
+            "min": -0.26196566224098206,
+            "max": 0.102737195789814,
+            "count": 242
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.00034723966382443905,
-            "min": -0.016603363677859306,
-            "max": 0.008311246521770954,
-            "count": 336
+            "value": -0.0008724190993234515,
+            "min": -0.024355709552764893,
+            "max": 0.007041024509817362,
+            "count": 242
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.004861355293542147,
-            "min": -0.20397886633872986,
-            "max": 0.14960244297981262,
-            "count": 336
+            "value": -0.013958705589175224,
+            "min": -0.2679128050804138,
+            "max": 0.08854017406702042,
+            "count": 242
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 336
+            "count": 242
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 336
+            "count": 242
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.10274285503796168,
-            "min": -0.6153846153846154,
-            "max": 0.30941333770751955,
-            "count": 336
+            "value": 0.0,
+            "min": -0.5,
+            "max": 0.25085714033671785,
+            "count": 242
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -1.4383999705314636,
-            "min": -8.0,
-            "max": 4.641200065612793,
-            "count": 336
+            "value": 0.0,
+            "min": -6.0,
+            "max": 4.1572000831365585,
+            "count": 242
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.10274285503796168,
-            "min": -0.6153846153846154,
-            "max": 0.30941333770751955,
-            "count": 336
+            "value": 0.0,
+            "min": -0.5,
+            "max": 0.25085714033671785,
+            "count": 242
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -1.4383999705314636,
-            "min": -8.0,
-            "max": 4.641200065612793,
-            "count": 336
+            "value": 0.0,
+            "min": -6.0,
+            "max": 4.1572000831365585,
+            "count": 242
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 336
+            "count": 242
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 336
+            "count": 242
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.018245630019130963,
-            "min": 0.010697820197674447,
-            "max": 0.02561476546494911,
-            "count": 156
+            "value": 0.017036540707340463,
+            "min": 0.01092280437393735,
+            "max": 0.022488900188667078,
+            "count": 112
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.018245630019130963,
-            "min": 0.010697820197674447,
-            "max": 0.02561476546494911,
-            "count": 156
+            "value": 0.017036540707340463,
+            "min": 0.01092280437393735,
+            "max": 0.022488900188667078,
+            "count": 112
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.0022934511187486352,
-            "min": 3.293917743008023e-08,
-            "max": 0.004799806737961868,
-            "count": 156
+            "value": 2.7369898816687055e-05,
+            "min": 1.643655115420491e-07,
+            "max": 0.004814238233181337,
+            "count": 112
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.0022934511187486352,
-            "min": 3.293917743008023e-08,
-            "max": 0.004799806737961868,
-            "count": 156
+            "value": 2.7369898816687055e-05,
+            "min": 1.643655115420491e-07,
+            "max": 0.004814238233181337,
+            "count": 112
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0022925760208939512,
-            "min": 3.4055962316870134e-08,
-            "max": 0.004811614612117409,
-            "count": 156
+            "value": 2.73141261307804e-05,
+            "min": 1.5780971776753934e-07,
+            "max": 0.004814112830596666,
+            "count": 112
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0022925760208939512,
-            "min": 3.4055962316870134e-08,
-            "max": 0.004811614612117409,
-            "count": 156
+            "value": 2.73141261307804e-05,
+            "min": 1.5780971776753934e-07,
+            "max": 0.004814112830596666,
+            "count": 112
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 156
+            "count": 112
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 156
+            "count": 112
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000004,
             "max": 0.20000000000000007,
-            "count": 156
+            "count": 112
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000004,
             "max": 0.20000000000000007,
-            "count": 156
+            "count": 112
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 156
+            "count": 112
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 156
+            "count": 112
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1724485830",
+        "start_time_seconds": "1724497816",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/poca/SoccerTwos_monti-python.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics --resume",
         "mlagents_version": "1.0.0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1724493952"
+        "end_time_seconds": "1724503464"
     },
-    "total": 8121.638562288004,
+    "total": 5648.517334780001,
     "count": 1,
-    "self": 2.7002768980164547,
+    "self": 0.27658308199897874,
     "children": {
         "run_training.setup": {
-            "total": 0.03839782899012789,
+            "total": 0.0332001950009726,
             "count": 1,
-            "self": 0.03839782899012789
+            "self": 0.0332001950009726
         },
         "TrainerController.start_learning": {
-            "total": 8118.899887560998,
+            "total": 5648.207551503001,
             "count": 1,
-            "self": 4.844773393328069,
+            "self": 3.444035428852658,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.095048737988691,
-                    "count": 18,
-                    "self": 6.095048737988691
+                    "total": 5.419610770026338,
+                    "count": 14,
+                    "self": 5.419610770026338
                 },
                 "TrainerController.advance": {
-                    "total": 8107.525918486674,
-                    "count": 218353,
-                    "self": 5.775869243690977,
+                    "total": 5639.084447214118,
+                    "count": 157405,
+                    "self": 3.953651600939338,
                     "children": {
                         "env_step": {
-                            "total": 6627.100370356347,
-                            "count": 218353,
-                            "self": 3971.8297717313253,
+                            "total": 4591.684293982689,
+                            "count": 157405,
+                            "self": 2794.746072800728,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 2651.698002098463,
-                                    "count": 218353,
-                                    "self": 45.84650845074793,
+                                    "total": 1794.5164113909996,
+                                    "count": 157405,
+                                    "self": 30.40238449710887,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 2605.851493647715,
-                                            "count": 433644,
-                                            "self": 2605.851493647715
+                                            "total": 1764.1140268938907,
+                                            "count": 312540,
+                                            "self": 1764.1140268938907
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 3.5725965265592095,
-                                    "count": 218353,
+                                    "total": 2.421809790961561,
+                                    "count": 157404,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 8107.719880896722,
-                                            "count": 218353,
+                                            "total": 5640.890048837231,
+                                            "count": 157404,
                                             "is_parallel": true,
-                                            "self": 4726.1546851361345,
+                                            "self": 3259.729416945236,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00359993199526798,
+                                                            "total": 0.003890229985699989,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0010267939942423254,
+                                                            "self": 0.0014303580101113766,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0025731380010256544,
+                                                                    "total": 0.0024598719755886123,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0025731380010256544
+                                                                    "self": 0.0024598719755886123
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.030910494999261573,
+                                                            "total": 0.03318805700109806,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006244039832381532,
+                                                            "self": 0.0006699319928884506,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005837830103700981,
+                                                                    "total": 0.0004741019947687164,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005837830103700981
+                                                                    "self": 0.0004741019947687164
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.02795641300326679,
+                                                                    "total": 0.029174192997743376,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.02795641300326679
+                                                                    "self": 0.029174192997743376
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017458950023865327,
+                                                                    "total": 0.0028698300156975165,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00047792399709578604,
+                                                                    "self": 0.0007267300534294918,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012679710052907467,
+                                                                            "total": 0.0021430999622680247,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012679710052907467
+                                                                            "self": 0.0021430999622680247
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.028173927988973446,
-                                                    "count": 34,
+                                                    "total": 0.019987581021268852,
+                                                    "count": 26,
                                                     "is_parallel": true,
-                                                    "self": 0.006554366031195968,
+                                                    "self": 0.004352420073701069,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.021619561957777478,
-                                                            "count": 136,
+                                                            "total": 0.015635160947567783,
+                                                            "count": 104,
                                                             "is_parallel": true,
-                                                            "self": 0.021619561957777478
+                                                            "self": 0.015635160947567783
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 3381.537021832599,
-                                                    "count": 218352,
+                                                    "total": 2381.1406443109736,
+                                                    "count": 157403,
                                                     "is_parallel": true,
-                                                    "self": 110.71889081182599,
+                                                    "self": 77.82742763230635,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 71.81114846019773,
-                                                            "count": 218352,
+                                                            "total": 50.70297598854813,
+                                                            "count": 157403,
                                                             "is_parallel": true,
-                                                            "self": 71.81114846019773
+                                                            "self": 50.70297598854813
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2845.843969446214,
-                                                            "count": 218352,
+                                                            "total": 2001.539421746449,
+                                                            "count": 157403,
                                                             "is_parallel": true,
-                                                            "self": 2845.843969446214
+                                                            "self": 2001.539421746449
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 353.1630131143611,
-                                                            "count": 436704,
+                                                            "total": 251.07081894367002,
+                                                            "count": 314806,
                                                             "is_parallel": true,
-                                                            "self": 76.61331705552584,
+                                                            "self": 54.14723351367866,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 276.54969605883525,
-                                                                    "count": 1746816,
+                                                                    "total": 196.92358542999136,
+                                                                    "count": 1259224,
                                                                     "is_parallel": true,
-                                                                    "self": 276.54969605883525
+                                                                    "self": 196.92358542999136
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1474.6496788866352,
-                            "count": 218353,
-                            "self": 45.66025243890181,
+                            "total": 1043.4465016304894,
+                            "count": 157404,
+                            "self": 32.840051461957046,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 529.129141788726,
-                                    "count": 218353,
-                                    "self": 526.1613544467255,
+                                    "total": 388.42192564149445,
+                                    "count": 157404,
+                                    "self": 386.8210518114938,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 2.96778734200052,
-                                            "count": 7,
-                                            "self": 2.96778734200052
+                                            "total": 1.600873830000637,
+                                            "count": 4,
+                                            "self": 1.600873830000637
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 899.8602846590074,
-                                    "count": 156,
-                                    "self": 504.49339664916624,
+                                    "total": 622.1845245270379,
+                                    "count": 112,
+                                    "self": 343.7758908315009,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 395.3668880098412,
-                                            "count": 4686,
-                                            "self": 395.3668880098412
+                                            "total": 278.408633695537,
+                                            "count": 3369,
+                                            "self": 278.408633695537
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.250055205076933e-07,
+                    "total": 1.1130032362416387e-06,
                     "count": 1,
-                    "self": 7.250055205076933e-07
+                    "self": 1.1130032362416387e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.4341462180018425,
+                    "total": 0.2594569770008093,
                     "count": 1,
-                    "self": 0.01243441599945072,
+                    "self": 0.004013034005765803,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.4217118020023918,
+                            "total": 0.25544394299504347,
                             "count": 1,
-                            "self": 0.4217118020023918
+                            "self": 0.25544394299504347
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 3499620,
-                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-3499620.onnx",
+                "steps": 5499120,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-5499120.onnx",
                 "reward": 0.0,
-                "creation_time": 1724490389.9830647,
+                "creation_time": 1724499003.2541206,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-3499620.pt"
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-5499120.pt"
                 ]
             },
             {
-                "steps": 3999601,
-                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-3999601.onnx",
+                "steps": 5999984,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-5999984.onnx",
                 "reward": 0.0,
-                "creation_time": 1724491590.8196423,
+                "creation_time": 1724500171.544804,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-3999601.pt"
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-5999984.pt"
                 ]
             },
             {
-                "steps": 4499882,
-                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-4499882.onnx",
+                "steps": 6499436,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-6499436.onnx",
                 "reward": 0.0,
-                "creation_time": 1724492797.5179863,
+                "creation_time": 1724501320.642419,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-4499882.pt"
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-6499436.pt"
                 ]
             },
             {
-                "steps": 4999694,
-                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-4999694.onnx",
+                "steps": 6999326,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-6999326.onnx",
                 "reward": 0.0,
-                "creation_time": 1724493949.0609605,
+                "creation_time": 1724502464.5354974,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-4999694.pt"
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-6999326.pt"
                 ]
             },
             {
-                "steps": 5001694,
-                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-5001694.onnx",
+                "steps": 7425648,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-7425648.onnx",
                 "reward": 0.0,
-                "creation_time": 1724493949.8066459,
+                "creation_time": 1724503464.3094752,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-5001694.pt"
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-7425648.pt"
                 ]
             }
         ],
-        "elo": 1187.7324242854907,
+        "elo": 1206.8610828455319,
         "final_checkpoint": {
-            "steps": 5001694,
+            "steps": 7425648,
             "file_path": "results/SoccerTwos1/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1724493949.8066459,
+            "creation_time": 1724503464.3094752,
             "auxillary_file_paths": [
-                "results/SoccerTwos1/SoccerTwos/SoccerTwos-5001694.pt"
+                "results/SoccerTwos1/SoccerTwos/SoccerTwos-7425648.pt"
             ]
         }
     },