13th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab0e9337b6f31cd3ff0be5c09d33b7878503e0b4eaa1f0144c60c8ea5342dad
+oid sha256:964e6e6118fab51b0b073b343f3f777c316b524f649fdd10ea62e6483d32c76f
 size 2351062

SoccerTwos/SoccerTwos-54557354.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964e6e6118fab51b0b073b343f3f777c316b524f649fdd10ea62e6483d32c76f
+size 2351062

SoccerTwos/SoccerTwos-54557354.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248fe9dbe3ae5693c00ac45a30f0e7a8cd08b09a7f1188328ac5a2b6a00dca08
+size 36303154

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d67e6f98598541bd87f1d88261a8f3f615c8208474d09adea24e28f619505d8f
+oid sha256:08cbe98fbf424e21a883c46cd61b3b9401d033e9c620488fc2d6ecc2794d1566
 size 36301318

SoccerTwos/events.out.tfevents.1725835611.Bretts-MacBook-Pro.local.69008.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2365e86f8b098b594d9e1317aa52c80067152cad57a80f5493012becd32041
+size 317321

SoccerTwos/events.out.tfevents.1725838368.Bretts-MacBook-Pro.local.16545.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3879544b02577bd81ad25a66360b467a31ba9e9d103dbe908ce93cb520d45cce
+size 317321

SoccerTwos/events.out.tfevents.1725841180.Bretts-MacBook-Pro.local.63471.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e55f9619e3d59799c52d724a24b30926c3fac10305a2cd8da6107ec245068a
+size 392003

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}, "curiosity": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.9, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "sept-run-01", "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": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}, "curiosity": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.5, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "sept-run-01", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -74,7 +74,7 @@ behaviors:
       team_change: 400000
       swap_steps: 2000
       window: 30
-      play_against_latest_model_ratio: 0.9
+      play_against_latest_model_ratio: 0.5
       initial_elo: 1.0
     behavioral_cloning: null
 env_settings:

run_logs/Player-0.log

@@ -10,7 +10,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.048 seconds
+- Completed reload, in  0.180 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)
@@ -35,17 +35,16 @@ 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: 0.230292 ms
+UnloadTime: 0.771458 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
-Thread 0x16fca3000 may have been prematurely finalized
+Thread 0x16d367000 may have been prematurely finalized
 Setting up 7 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]: 437419 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 6921 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
@@ -68,7 +67,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 6]
       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 0]
       Initial Block Size 256.0 KB
@@ -173,7 +172,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 7]
       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 1]
       Initial Block Size 256.0 KB
@@ -226,22 +225,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 15
+  Peak main deferred allocation count 3
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.1 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 437420 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 6922 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.1 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]: 437420 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 6922 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -268,15 +267,15 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.1 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 437419 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 6921 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]: 437420 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 6922 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -286,15 +285,15 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.1 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 437420 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 6922 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]: 437419 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 6921 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 3.4 MB
@@ -304,15 +303,15 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.1 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 437420 frames
+      Peak usage frame count: [0-1.0 KB]: 6922 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]: 437419 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 6921 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

@@ -2,309 +2,309 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.001605272293091,
-            "min": 1.9789596796035767,
-            "max": 2.2079057693481445,
-            "count": 2328
+            "value": 1.9969096183776855,
+            "min": 1.9881949424743652,
+            "max": 2.0352447032928467,
+            "count": 37
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 38879.1796875,
-            "min": 18002.392578125,
-            "max": 50645.35546875,
-            "count": 2328
+            "value": 38979.67578125,
+            "min": 5781.62890625,
+            "max": 46117.58984375,
+            "count": 37
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 63.63636363636363,
-            "min": 48.584158415841586,
-            "max": 102.3061224489796,
-            "count": 2328
+            "value": 65.62162162162163,
+            "min": 32.84615384615385,
+            "max": 80.7,
+            "count": 37
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19600.0,
-            "min": 5596.0,
-            "max": 21380.0,
-            "count": 2328
+            "value": 19424.0,
+            "min": 1708.0,
+            "max": 20628.0,
+            "count": 37
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 195.8465984461809,
-            "min": 75.29896745804021,
-            "max": 227.62322024749807,
-            "count": 2328
+            "value": 198.21202946222434,
+            "min": 179.02586237338554,
+            "max": 218.34975734283196,
+            "count": 37
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 30160.376160711858,
-            "min": 4495.842920529803,
-            "max": 44901.73591040075,
-            "count": 2328
+            "value": 29335.380360409203,
+            "min": 5077.5757329704975,
+            "max": 37254.03187139414,
+            "count": 37
         },
         "SoccerTwos.Step.mean": {
-            "value": 54179992.0,
-            "min": 30909902.0,
-            "max": 54179992.0,
-            "count": 2328
+            "value": 54549966.0,
+            "min": 54189950.0,
+            "max": 54549966.0,
+            "count": 37
         },
         "SoccerTwos.Step.sum": {
-            "value": 54179992.0,
-            "min": 30909902.0,
-            "max": 54179992.0,
-            "count": 2328
+            "value": 54549966.0,
+            "min": 54189950.0,
+            "max": 54549966.0,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.029384715482592583,
-            "min": -0.25675803422927856,
-            "max": 0.19587919116020203,
-            "count": 2328
+            "value": -0.007430660538375378,
+            "min": -0.13059571385383606,
+            "max": 0.0799141526222229,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -4.5252461433410645,
-            "min": -37.743431091308594,
-            "max": 28.20660400390625,
-            "count": 2328
+            "value": -1.0997377634048462,
+            "min": -18.02220916748047,
+            "max": 12.706350326538086,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.029946662485599518,
-            "min": -0.25568994879722595,
-            "max": 0.194318026304245,
-            "count": 2328
+            "value": -0.010138335637748241,
+            "min": -0.13116949796676636,
+            "max": 0.0780540257692337,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -4.611785888671875,
-            "min": -37.586421966552734,
-            "max": 27.981796264648438,
-            "count": 2328
+            "value": -1.5004737377166748,
+            "min": -18.101390838623047,
+            "max": 12.410590171813965,
+            "count": 37
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
-            "value": 7.706054748268798e-05,
-            "min": -0.0007188767194747925,
-            "max": 0.0051978351548314095,
-            "count": 2328
+            "value": 0.0002736914320848882,
+            "min": -6.777280214009807e-05,
+            "max": 0.0012276290217414498,
+            "count": 37
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
-            "value": 0.011867323890328407,
-            "min": -0.10208049416542053,
-            "max": 0.6841692924499512,
-            "count": 2328
+            "value": 0.040506333112716675,
+            "min": -0.009352646768093109,
+            "max": 0.17432332038879395,
+            "count": 37
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
-            "value": 0.0001772618415998295,
-            "min": -0.0007160860113799572,
-            "max": 0.004996820818632841,
-            "count": 2328
+            "value": 0.00035474830656312406,
+            "min": -5.8898836869047955e-05,
+            "max": 0.0012730894377455115,
+            "count": 37
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
-            "value": 0.027298323810100555,
-            "min": -0.10168421268463135,
-            "max": 0.6836073398590088,
-            "count": 2328
+            "value": 0.052502747625112534,
+            "min": -0.008128039538860321,
+            "max": 0.18077869713306427,
+            "count": 37
         },
         "SoccerTwos.Policy.RndBaselineEstimate.mean": {
-            "value": 2.2803717001806945e-05,
-            "min": -0.0007127210847102106,
-            "max": 0.0004282182489987463,
-            "count": 2328
+            "value": -5.368301572161727e-06,
+            "min": -0.0004969912697561085,
+            "max": 3.707858923007734e-05,
+            "count": 37
         },
         "SoccerTwos.Policy.RndBaselineEstimate.sum": {
-            "value": 0.0035117724910378456,
-            "min": -0.11374851316213608,
-            "max": 0.07644464075565338,
-            "count": 2328
+            "value": -0.0007945086108520627,
+            "min": -0.011927790008485317,
+            "max": 0.005265159532427788,
+            "count": 37
         },
         "SoccerTwos.Policy.RndValueEstimate.mean": {
-            "value": 2.6185234673903324e-05,
-            "min": -0.000715779431629926,
-            "max": 0.0004273174563422799,
-            "count": 2328
+            "value": -1.8312478005100274e-06,
+            "min": -0.0005034385831095278,
+            "max": 3.7688361771870404e-05,
+            "count": 37
         },
         "SoccerTwos.Policy.RndValueEstimate.sum": {
-            "value": 0.0040325261652469635,
-            "min": -0.11362162232398987,
-            "max": 0.07622122019529343,
-            "count": 2328
+            "value": -0.00027102467720396817,
+            "min": -0.012082526460289955,
+            "max": 0.005294247530400753,
+            "count": 37
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 2328
+            "count": 37
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 2328
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.0681636356688165,
-            "min": -0.3762892068718835,
-            "max": 0.33065000329262173,
-            "count": 2328
+            "value": 0.016586483330339997,
+            "min": -0.34476666649182636,
+            "max": 0.25351304420526477,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -10.497199892997742,
-            "min": -59.05200004577637,
-            "max": 51.58140051364899,
-            "count": 2328
+            "value": 2.45479953289032,
+            "min": -37.585999965667725,
+            "max": 36.569599866867065,
+            "count": 37
         },
         "SoccerTwos.Policy.CuriosityReward.mean": {
-            "value": 2.6100170660580945e-06,
+            "value": 4.499394341982642e-06,
             "min": 0.0,
-            "max": 6.030737767756281e-06,
-            "count": 2328
+            "max": 5.611564276982197e-06,
+            "count": 37
         },
         "SoccerTwos.Policy.CuriosityReward.sum": {
-            "value": 0.00040194262817294657,
+            "value": 0.0006659103626134311,
             "min": 0.0,
-            "max": 0.000809542730053181,
-            "count": 2328
+            "max": 0.0007855380640080512,
+            "count": 37
         },
         "SoccerTwos.Policy.RndReward.mean": {
-            "value": 1.19658387680894e-06,
-            "min": 8.922438388125897e-07,
-            "max": 1.9774367168225843e-06,
-            "count": 2328
+            "value": 1.2830813336731009e-06,
+            "min": 4.958954645436128e-07,
+            "max": 1.5597248766810985e-06,
+            "count": 37
         },
         "SoccerTwos.Policy.RndReward.sum": {
-            "value": 0.00018427391702857676,
-            "min": 6.0544335880763356e-05,
-            "max": 0.000219697240559924,
-            "count": 2328
+            "value": 0.00018989603738361893,
+            "min": 1.1901491149046706e-05,
+            "max": 0.0002003613023049411,
+            "count": 37
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.0681636356688165,
-            "min": -0.3762892068718835,
-            "max": 0.33065000329262173,
-            "count": 2328
+            "value": 0.016586483330339997,
+            "min": -0.34476666649182636,
+            "max": 0.25351304420526477,
+            "count": 37
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -10.497199892997742,
-            "min": -59.05200004577637,
-            "max": 51.58140051364899,
-            "count": 2328
+            "value": 2.45479953289032,
+            "min": -37.585999965667725,
+            "max": 36.569599866867065,
+            "count": 37
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2328
+            "count": 37
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2328
+            "count": 37
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.011342826396382103,
-            "min": 0.005190658658345153,
-            "max": 0.019213409415291,
-            "count": 157
+            "value": 0.014808606375784924,
+            "min": 0.004393496378421939,
+            "max": 0.014808606375784924,
+            "count": 2
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.011342826396382103,
-            "min": 0.005190658658345153,
-            "max": 0.019213409415291,
-            "count": 157
+            "value": 0.014808606375784924,
+            "min": 0.004393496378421939,
+            "max": 0.014808606375784924,
+            "count": 2
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.0180530430128177,
-            "min": 0.016259409797688324,
-            "max": 0.023114188263813656,
-            "count": 157
+            "value": 0.017829062106708687,
+            "min": 0.017829062106708687,
+            "max": 0.0180764712082843,
+            "count": 2
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.0180530430128177,
-            "min": 0.016259409797688324,
-            "max": 0.023114188263813656,
-            "count": 157
+            "value": 0.017829062106708687,
+            "min": 0.017829062106708687,
+            "max": 0.0180764712082843,
+            "count": 2
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.01849161460995674,
-            "min": 0.016563859457770985,
-            "max": 0.02328170510008931,
-            "count": 157
+            "value": 0.018067089995990198,
+            "min": 0.018067089995990198,
+            "max": 0.018403542538483936,
+            "count": 2
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.01849161460995674,
-            "min": 0.016563859457770985,
-            "max": 0.02328170510008931,
-            "count": 157
+            "value": 0.018067089995990198,
+            "min": 0.018067089995990198,
+            "max": 0.018403542538483936,
+            "count": 2
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 157
+            "count": 2
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 157
+            "count": 2
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000004,
             "min": 0.20000000000000004,
             "max": 0.20000000000000004,
-            "count": 157
+            "count": 2
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000004,
             "min": 0.20000000000000004,
             "max": 0.20000000000000004,
-            "count": 157
+            "count": 2
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.0032458374235,
-            "min": 0.0032458374235,
-            "max": 0.0061222651165,
-            "count": 157
+            "value": 0.003196297762750001,
+            "min": 0.003196297762750001,
+            "max": 0.0032146366555,
+            "count": 2
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.0032458374235,
-            "min": 0.0032458374235,
-            "max": 0.0061222651165,
-            "count": 157
+            "value": 0.003196297762750001,
+            "min": 0.003196297762750001,
+            "max": 0.0032146366555,
+            "count": 2
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.04033469967544079,
-            "min": 0.03939711768180132,
-            "max": 0.13589541738231978,
-            "count": 157
+            "value": 0.06618556349227826,
+            "min": 0.06618556349227826,
+            "max": 0.14213946927338839,
+            "count": 2
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.sum": {
-            "value": 0.04033469967544079,
-            "min": 0.03939711768180132,
-            "max": 0.13589541738231978,
-            "count": 157
+            "value": 0.06618556349227826,
+            "min": 0.06618556349227826,
+            "max": 0.14213946927338839,
+            "count": 2
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.mean": {
-            "value": 1.4537008007367451,
-            "min": 1.4515005846818287,
-            "max": 1.8242186109224956,
-            "count": 157
+            "value": 1.5162039995193481,
+            "min": 1.5162039995193481,
+            "max": 1.7156379719575245,
+            "count": 2
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.sum": {
-            "value": 1.4537008007367451,
-            "min": 1.4515005846818287,
-            "max": 1.8242186109224956,
-            "count": 157
+            "value": 1.5162039995193481,
+            "min": 1.5162039995193481,
+            "max": 1.7156379719575245,
+            "count": 2
         },
         "SoccerTwos.Losses.RNDLoss.mean": {
-            "value": 0.016839604824781418,
-            "min": 0.016614088788628578,
-            "max": 0.01993536204099655,
-            "count": 157
+            "value": 0.01695634238421917,
+            "min": 0.01695634238421917,
+            "max": 0.018619608134031296,
+            "count": 2
         },
         "SoccerTwos.Losses.RNDLoss.sum": {
-            "value": 0.016839604824781418,
-            "min": 0.016614088788628578,
-            "max": 0.01993536204099655,
-            "count": 157
+            "value": 0.01695634238421917,
+            "min": 0.01695634238421917,
+            "max": 0.018619608134031296,
+            "count": 2
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1725741370",
+        "start_time_seconds": "1725841167",
         "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
         "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume --no-graphics",
         "mlagents_version": "1.1.0.dev0",
@@ -312,103 +312,103 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.0",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1725834732"
+        "end_time_seconds": "1725842676"
     },
-    "total": 93361.07623400001,
+    "total": 1508.5802902500145,
     "count": 1,
-    "self": 0.2508249579987023,
+    "self": 0.21788324997760355,
     "children": {
         "run_training.setup": {
-            "total": 0.02454258399666287,
+            "total": 0.04177620803238824,
             "count": 1,
-            "self": 0.02454258399666287
+            "self": 0.04177620803238824
         },
         "TrainerController.start_learning": {
-            "total": 93360.80086645801,
+            "total": 1508.3206307920045,
             "count": 1,
-            "self": 14.692869420541683,
+            "self": 0.3137190431007184,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.080348207993666,
-                    "count": 60,
-                    "self": 6.080348207993666
+                    "total": 18.376407083997037,
+                    "count": 2,
+                    "self": 18.376407083997037
                 },
                 "TrainerController.advance": {
-                    "total": 93339.84131478748,
-                    "count": 1596200,
-                    "self": 12.974666123162024,
+                    "total": 1489.5077864558552,
+                    "count": 25276,
+                    "self": 0.2775827504810877,
                     "children": {
                         "env_step": {
-                            "total": 64851.92356695773,
-                            "count": 1596200,
-                            "self": 62650.110620818625,
+                            "total": 1123.7648561956594,
+                            "count": 25276,
+                            "self": 1078.8828879335197,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 2192.282666757237,
-                                    "count": 1596200,
-                                    "self": 89.96115429818747,
+                                    "total": 44.72521206212696,
+                                    "count": 25276,
+                                    "self": 2.0787426518509164,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 2102.3215124590497,
-                                            "count": 2916144,
-                                            "self": 2102.3215124590497
+                                            "total": 42.64646941027604,
+                                            "count": 46144,
+                                            "self": 42.64646941027604
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 9.53027938187006,
-                                    "count": 1596199,
+                                    "total": 0.15675620001275092,
+                                    "count": 25275,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 93334.78617089201,
-                                            "count": 1596199,
+                                            "total": 1495.4258725288673,
+                                            "count": 25275,
                                             "is_parallel": true,
-                                            "self": 32393.573468669725,
+                                            "self": 445.4487812644802,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.08119578479090706,
-                                                    "count": 120,
+                                                    "total": 0.014769584115128964,
+                                                    "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.010500200296519324,
+                                                    "self": 0.0022344160825014114,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.07069558449438773,
-                                                            "count": 480,
+                                                            "total": 0.012535168032627553,
+                                                            "count": 16,
                                                             "is_parallel": true,
-                                                            "self": 0.07069558449438773
+                                                            "self": 0.012535168032627553
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 60941.131506437494,
-                                                    "count": 1596199,
+                                                    "total": 1049.962321680272,
+                                                    "count": 25275,
                                                     "is_parallel": true,
-                                                    "self": 159.10876413882943,
+                                                    "self": 2.7510678524849936,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 1219.8835514431412,
-                                                            "count": 1596199,
+                                                            "total": 20.389946024806704,
+                                                            "count": 25275,
                                                             "is_parallel": true,
-                                                            "self": 1219.8835514431412
+                                                            "self": 20.389946024806704
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 57588.91226845488,
-                                                            "count": 1596199,
+                                                            "total": 991.4256553296,
+                                                            "count": 25275,
                                                             "is_parallel": true,
-                                                            "self": 57588.91226845488
+                                                            "self": 991.4256553296
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 1973.226922400645,
-                                                            "count": 3192398,
+                                                            "total": 35.39565247338032,
+                                                            "count": 50550,
                                                             "is_parallel": true,
-                                                            "self": 236.34830627954216,
+                                                            "self": 4.224398136662785,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1736.8786161211028,
-                                                                    "count": 12769592,
+                                                                    "total": 31.17125433671754,
+                                                                    "count": 202200,
                                                                     "is_parallel": true,
-                                                                    "self": 1736.8786161211028
+                                                                    "self": 31.17125433671754
                                                                 }
                                                             }
                                                         }
@@ -421,31 +421,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 28474.943081706588,
-                            "count": 1596199,
-                            "self": 129.82655392051674,
+                            "total": 365.4653475097148,
+                            "count": 25275,
+                            "self": 1.8992199255153537,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 5061.878445453796,
-                                    "count": 1596199,
-                                    "self": 5053.8462954926945,
+                                    "total": 89.4906855011941,
+                                    "count": 25275,
+                                    "self": 89.27783558517694,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 8.032149961101823,
-                                            "count": 47,
-                                            "self": 8.032149961101823
+                                            "total": 0.21284991601714864,
+                                            "count": 1,
+                                            "self": 0.21284991601714864
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 23283.238082332275,
-                                    "count": 157,
-                                    "self": 2272.794731600414,
+                                    "total": 274.0754420830053,
+                                    "count": 2,
+                                    "self": 27.831998248002492,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 21010.44335073186,
-                                            "count": 1884,
-                                            "self": 21010.44335073186
+                                            "total": 246.24344383500284,
+                                            "count": 24,
+                                            "self": 246.24344383500284
                                         }
                                     }
                                 }
@@ -454,19 +454,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.169996827840805e-07,
+                    "total": 4.5902561396360397e-07,
                     "count": 1,
-                    "self": 4.169996827840805e-07
+                    "self": 4.5902561396360397e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.18633362499531358,
+                    "total": 0.12271775002591312,
                     "count": 1,
-                    "self": 0.0009461659938097,
+                    "self": 0.00397670897655189,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18538745900150388,
+                            "total": 0.11874104104936123,
                             "count": 1,
-                            "self": 0.18538745900150388
+                            "self": 0.11874104104936123
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,24 @@
 {
     "SoccerTwos": {
-        "elo": 195.29137434501916,
+        "elo": 217.01995127360857,
         "checkpoints": [
             {
-                "steps": 54189194,
-                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-54189194.onnx",
+                "steps": 54557354,
+                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-54557354.onnx",
                 "reward": 0.0,
-                "creation_time": 1725834731.7809012,
+                "creation_time": 1725842676.0499809,
                 "auxillary_file_paths": [
-                    "results/sept-run-01/SoccerTwos/SoccerTwos-54189194.pt"
+                    "results/sept-run-01/SoccerTwos/SoccerTwos-54557354.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 54189194,
+            "steps": 54557354,
             "file_path": "results/sept-run-01/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1725834731.7809012,
+            "creation_time": 1725842676.0499809,
             "auxillary_file_paths": [
-                "results/sept-run-01/SoccerTwos/SoccerTwos-54189194.pt"
+                "results/sept-run-01/SoccerTwos/SoccerTwos-54557354.pt"
             ]
         }
     },