22th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe445853fd261a72561815d3f0df34585061e80f258877a46e6cfb872503241e
+oid sha256:69b51b07ec91e34ed1dabecfd030b2bbdc412154d6ed172175e1e370b4d15970
 size 2351062

SoccerTwos/SoccerTwos-167999965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2688a5d804e12c7f5ecf788d6bbc7f4b9438be3fb2923eb794408439f98d0110
+size 2351062

SoccerTwos/SoccerTwos-167999965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2928405bc316b847dee90c71b292c2960cbf170c6412e1ff61451a64904e7084
+size 36303358

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87dfdf0a17b7f2ee2263a29472450daaa8afc206f05fb7b44411ead182ab141d
+oid sha256:29c9d914dd2ac288cdcba1f5814d00974c9feb2685d6b1c34d785865b03c8dbd
 size 36301318

SoccerTwos/events.out.tfevents.1726856751.Bretts-MBP.home.93804.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81b38d6302e02ae3a43ada162d92bc8e85dd8107eb49222a78ead5406e0d27d
-size 613337
+oid sha256:b384b3949f3c1594a24127a9c255f639f3abc4bcc629181867b00def6de5cc31
+size 697991

SoccerTwos/events.out.tfevents.1726859736.Bretts-MBP.home.96805.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25fc0ea19114fb78f3af377fba59f00d75f9e857061cb94831d95dba673a25d0
+size 2596477

SoccerTwos/events.out.tfevents.1726870995.Bretts-MBP.home.56206.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ff0182d4f0593c0a6f743cbbc5b2f862b94a95f3036df7728e2c3b2b6a0376
+size 3218428

SoccerTwos/events.out.tfevents.1726884863.Bretts-MBP.home.94944.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4426f2975fedc0d03736454fc7f054d62f64d3f9596fbebe95f8cf9232a5b4
+size 7775107

SoccerTwos/events.out.tfevents.1726918210.Bretts-MBP.home.52092.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4c13e46f8a0dda4f52b47e4b8761ad550a9ded53f5cfb6fc9853e5898dd1ae
+size 8534287

SoccerTwos/events.out.tfevents.1726955165.Bretts-MBP.home.22508.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2f63c6bd869ebe10da28e9771d7c0b3baa135f82f4349fd6dfe51b47545fe0
+size 9800301

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.3, "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": 0.999, "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": 0.5, "strength": 0.2, "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": 0.5, "strength": 0.2, "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": 10000000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 500000, "team_change": 10000, "swap_steps": 500, "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}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 60000, "buffer_size": 180000, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.3, "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": 0.999, "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": 0.7, "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": 0.7, "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": 10000000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 500000, "team_change": 10000, "swap_steps": 500, "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}

configuration.yaml

@@ -3,8 +3,8 @@ behaviors:
   SoccerTwos:
     trainer_type: poca
     hyperparameters:
-      batch_size: 40960
-      buffer_size: 163840
+      batch_size: 60000
+      buffer_size: 180000
       learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.3
@@ -37,8 +37,8 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
       curiosity:
-        gamma: 0.5
-        strength: 0.2
+        gamma: 0.7
+        strength: 1.0e-06
         network_settings:
           normalize: false
           hidden_units: 512
@@ -50,8 +50,8 @@ behaviors:
         learning_rate: 0.0003
         encoding_size: 512
       rnd:
-        gamma: 0.5
-        strength: 0.2
+        gamma: 0.7
+        strength: 1.0e-06
         network_settings:
           normalize: false
           hidden_units: 128
@@ -74,7 +74,7 @@ behaviors:
       team_change: 10000
       swap_steps: 500
       window: 30
-      play_against_latest_model_ratio: 0.5
+      play_against_latest_model_ratio: 0.9
       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  0.049 seconds
+- Completed reload, in  0.059 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)
@@ -35,7 +35,6 @@ 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: 0.294958 ms
+UnloadTime: 0.249500 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.

run_logs/timers.json

@@ -2,309 +2,309 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.013183355331421,
-            "min": 1.9969563484191895,
-            "max": 2.0372118949890137,
-            "count": 73
+            "value": 1.9824453592300415,
+            "min": 1.8739594221115112,
+            "max": 1.9862821102142334,
+            "count": 809
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 44515.51171875,
-            "min": 36500.25,
-            "max": 49285.63671875,
-            "count": 73
+            "value": 47261.49609375,
+            "min": 28590.546875,
+            "max": 53229.98828125,
+            "count": 809
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 67.79452054794521,
-            "min": 53.31521739130435,
-            "max": 84.3,
-            "count": 73
+            "value": 60.3974358974359,
+            "min": 48.78,
+            "max": 91.82142857142857,
+            "count": 809
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19796.0,
-            "min": 15476.0,
-            "max": 20316.0,
-            "count": 73
+            "value": 18844.0,
+            "min": 12724.0,
+            "max": 21204.0,
+            "count": 809
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 226.28569760195467,
-            "min": 218.50462034121867,
-            "max": 246.13217966828475,
-            "count": 73
+            "value": 200.69807122695505,
+            "min": 160.45223766886883,
+            "max": 221.11645994002805,
+            "count": 809
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 33037.71184988538,
-            "min": 25960.237905448797,
-            "max": 43074.66286109567,
-            "count": 73
+            "value": 31308.899111404986,
+            "min": 19529.90994427994,
+            "max": 40985.056697454515,
+            "count": 809
         },
         "SoccerTwos.Step.mean": {
-            "value": 137269836.0,
-            "min": 136549984.0,
-            "max": 137269836.0,
-            "count": 73
+            "value": 158899961.0,
+            "min": 150819962.0,
+            "max": 158899961.0,
+            "count": 809
         },
         "SoccerTwos.Step.sum": {
-            "value": 137269836.0,
-            "min": 136549984.0,
-            "max": 137269836.0,
-            "count": 73
+            "value": 158899961.0,
+            "min": 150819962.0,
+            "max": 158899961.0,
+            "count": 809
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.03741655498743057,
-            "min": -0.1345166116952896,
-            "max": 0.07524154335260391,
-            "count": 73
+            "value": -0.018284762278199196,
+            "min": -0.21704299747943878,
+            "max": 0.03359431400895119,
+            "count": 809
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -5.425400733947754,
-            "min": -21.791690826416016,
-            "max": 12.529707908630371,
-            "count": 73
+            "value": -2.8707077503204346,
+            "min": -36.11267852783203,
+            "max": 5.475872993469238,
+            "count": 809
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.03817114606499672,
-            "min": -0.1369057297706604,
-            "max": 0.07655324786901474,
-            "count": 73
+            "value": -0.03882867470383644,
+            "min": -0.2731809616088867,
+            "max": 0.03336219862103462,
+            "count": 809
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -5.534816265106201,
-            "min": -22.178728103637695,
-            "max": 12.63769817352295,
-            "count": 73
+            "value": -6.096101760864258,
+            "min": -49.92552947998047,
+            "max": 5.438038349151611,
+            "count": 809
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
-            "value": 0.022628309205174446,
-            "min": 0.009245038963854313,
-            "max": 0.02489888109266758,
-            "count": 73
+            "value": 1.2157836863480043e-05,
+            "min": -0.006319624371826649,
+            "max": 0.028939656913280487,
+            "count": 809
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
-            "value": 3.281104803085327,
-            "min": 1.175850749015808,
-            "max": 4.356385231018066,
-            "count": 73
+            "value": 0.0019087804248556495,
+            "min": -1.1164512634277344,
+            "max": 5.231081008911133,
+            "count": 809
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
-            "value": 0.02262844890356064,
-            "min": 0.009272996336221695,
-            "max": 0.024900028482079506,
-            "count": 73
+            "value": 5.69396479477291e-06,
+            "min": -0.006349184550344944,
+            "max": 0.02884219028055668,
+            "count": 809
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
-            "value": 3.281125068664551,
-            "min": 1.1755244731903076,
-            "max": 4.360075950622559,
-            "count": 73
+            "value": 0.0008939524996094406,
+            "min": -1.119166374206543,
+            "max": 5.209883689880371,
+            "count": 809
         },
         "SoccerTwos.Policy.RndBaselineEstimate.mean": {
-            "value": 0.006809944752603769,
-            "min": 0.006517637521028519,
-            "max": 0.007117425091564655,
-            "count": 73
+            "value": 8.368616363441106e-06,
+            "min": -0.00480329105630517,
+            "max": 0.0183656495064497,
+            "count": 809
         },
         "SoccerTwos.Policy.RndBaselineEstimate.sum": {
-            "value": 0.9874419569969177,
-            "min": 0.7655903697013855,
-            "max": 1.253800392150879,
-            "count": 73
+            "value": 0.0013138727517798543,
+            "min": -0.8429449796676636,
+            "max": 2.9267921447753906,
+            "count": 809
         },
         "SoccerTwos.Policy.RndValueEstimate.mean": {
-            "value": 0.006798093672841787,
-            "min": 0.006493216380476952,
-            "max": 0.0071043046191334724,
-            "count": 73
+            "value": 1.1133872249047272e-05,
+            "min": -0.004795185290277004,
+            "max": 0.0181350726634264,
+            "count": 809
         },
         "SoccerTwos.Policy.RndValueEstimate.sum": {
-            "value": 0.985723614692688,
-            "min": 0.7624234557151794,
-            "max": 1.2502329349517822,
-            "count": 73
+            "value": 0.001748017966747284,
+            "min": -0.8428221940994263,
+            "max": 2.9356842041015625,
+            "count": 809
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 73
+            "count": 809
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 73
+            "count": 809
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.10613517309057302,
-            "min": -0.2378641970363664,
-            "max": 0.25296296190332485,
-            "count": 73
+            "value": 0.1667643314713885,
+            "min": -0.3838250016172727,
+            "max": 0.2926405072212219,
+            "count": 809
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -15.389600098133087,
-            "min": -38.53399991989136,
-            "max": 34.14999985694885,
-            "count": 73
+            "value": 26.182000041007996,
+            "min": -57.72960007190704,
+            "max": 46.237200140953064,
+            "count": 809
         },
         "SoccerTwos.Policy.CuriosityReward.mean": {
-            "value": 0.6438479568038521,
+            "value": 2.6344333327928046e-06,
             "min": 0.0,
-            "max": 1.4505344783266385,
-            "count": 73
+            "max": 7.510302272501776e-06,
+            "count": 809
         },
         "SoccerTwos.Policy.CuriosityReward.sum": {
-            "value": 93.35795373655856,
+            "value": 0.00041360603324847034,
             "min": 0.0,
-            "max": 175.77997627854347,
-            "count": 73
+            "max": 0.001016018376105876,
+            "count": 809
         },
         "SoccerTwos.Policy.RndReward.mean": {
-            "value": 0.24667795498951756,
-            "min": 0.1884528696688043,
-            "max": 0.30395433399050187,
-            "count": 73
+            "value": 1.084395531976697e-06,
+            "min": 8.522362944063389e-07,
+            "max": 1.6413188463521214e-06,
+            "count": 809
         },
         "SoccerTwos.Policy.RndReward.sum": {
-            "value": 35.768303473480046,
-            "min": 27.970972408540547,
-            "max": 37.355501416139305,
-            "count": 73
+            "value": 0.00017025009852034145,
+            "min": 0.00011363447274703731,
+            "max": 0.00020103728658682485,
+            "count": 809
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.10613517309057302,
-            "min": -0.2378641970363664,
-            "max": 0.25296296190332485,
-            "count": 73
+            "value": 0.1667643314713885,
+            "min": -0.3838250016172727,
+            "max": 0.2926405072212219,
+            "count": 809
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -15.389600098133087,
-            "min": -38.53399991989136,
-            "max": 34.14999985694885,
-            "count": 73
+            "value": 26.182000041007996,
+            "min": -57.72960007190704,
+            "max": 46.237200140953064,
+            "count": 809
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 73
+            "count": 809
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 73
+            "count": 809
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.005562455854184615,
-            "min": 0.005562455854184615,
-            "max": 0.014488776432699524,
-            "count": 4
+            "value": 0.01488200124974052,
+            "min": 0.004595218287755011,
+            "max": 0.05061443419092231,
+            "count": 49
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.005562455854184615,
-            "min": 0.005562455854184615,
-            "max": 0.014488776432699524,
-            "count": 4
+            "value": 0.01488200124974052,
+            "min": 0.004595218287755011,
+            "max": 0.05061443419092231,
+            "count": 49
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.019290074861298006,
-            "min": 0.01834545625994603,
-            "max": 0.019290074861298006,
-            "count": 4
+            "value": 0.02260305318567488,
+            "min": 0.022456115318669215,
+            "max": 0.024703273756636515,
+            "count": 49
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.019290074861298006,
-            "min": 0.01834545625994603,
-            "max": 0.019290074861298006,
-            "count": 4
+            "value": 0.02260305318567488,
+            "min": 0.022456115318669215,
+            "max": 0.024703273756636515,
+            "count": 49
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.019729879529525835,
-            "min": 0.018973414786159992,
-            "max": 0.019729879529525835,
-            "count": 4
+            "value": 0.023345176751414936,
+            "min": 0.023041918666826353,
+            "max": 0.027839177805516455,
+            "count": 49
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.019729879529525835,
-            "min": 0.018973414786159992,
-            "max": 0.019729879529525835,
-            "count": 4
+            "value": 0.023345176751414936,
+            "min": 0.023041918666826353,
+            "max": 0.027839177805516455,
+            "count": 49
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 4
+            "count": 49
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 4
+            "count": 49
         },
         "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.29999999999999993,
-            "min": 0.29999999999999993,
-            "max": 0.29999999999999993,
-            "count": 4
+            "value": 0.3,
+            "min": 0.3,
+            "max": 0.3,
+            "count": 49
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.29999999999999993,
-            "min": 0.29999999999999993,
-            "max": 0.29999999999999993,
-            "count": 4
+            "value": 0.3,
+            "min": 0.3,
+            "max": 0.3,
+            "count": 49
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.004931572211836001,
-            "min": 0.004931572211836001,
-            "max": 0.0049317921091599996,
-            "count": 4
+            "value": 0.00492078891964,
+            "min": 0.00492078891964,
+            "max": 0.004924663299352,
+            "count": 49
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.004931572211836001,
-            "min": 0.004931572211836001,
-            "max": 0.0049317921091599996,
-            "count": 4
+            "value": 0.00492078891964,
+            "min": 0.00492078891964,
+            "max": 0.004924663299352,
+            "count": 49
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.0483112009242177,
-            "min": 0.0483112009242177,
-            "max": 0.1390404033785065,
-            "count": 4
+            "value": 0.04242806674705611,
+            "min": 0.0423487921555837,
+            "max": 0.12206676105658214,
+            "count": 49
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.sum": {
-            "value": 0.0483112009242177,
-            "min": 0.0483112009242177,
-            "max": 0.1390404033785065,
-            "count": 4
+            "value": 0.04242806674705611,
+            "min": 0.0423487921555837,
+            "max": 0.12206676105658214,
+            "count": 49
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.mean": {
-            "value": 1.3768685559431713,
-            "min": 1.3768685559431713,
-            "max": 1.6764498154322307,
-            "count": 4
+            "value": 1.361588226424323,
+            "min": 1.3439784447352092,
+            "max": 1.7959681616889105,
+            "count": 49
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.sum": {
-            "value": 1.3768685559431713,
-            "min": 1.3768685559431713,
-            "max": 1.6764498154322307,
-            "count": 4
+            "value": 1.361588226424323,
+            "min": 1.3439784447352092,
+            "max": 1.7959681616889105,
+            "count": 49
         },
         "SoccerTwos.Losses.RNDLoss.mean": {
-            "value": 0.015932753682136536,
-            "min": 0.01591380685567856,
-            "max": 0.017608152702450752,
-            "count": 4
+            "value": 0.015596083365380764,
+            "min": 0.015499476343393326,
+            "max": 0.017794109880924225,
+            "count": 49
         },
         "SoccerTwos.Losses.RNDLoss.sum": {
-            "value": 0.015932753682136536,
-            "min": 0.01591380685567856,
-            "max": 0.017608152702450752,
-            "count": 4
+            "value": 0.015596083365380764,
+            "min": 0.015499476343393326,
+            "max": 0.017794109880924225,
+            "count": 49
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1726852025",
+        "start_time_seconds": "1726918206",
         "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": "1726855117"
+        "end_time_seconds": "1726955045"
     },
-    "total": 3091.2703225830337,
+    "total": 36838.19481516699,
     "count": 1,
-    "self": 0.013066916028037667,
+    "self": 0.011806167894974351,
     "children": {
         "run_training.setup": {
-            "total": 0.019244292052462697,
+            "total": 0.019822541042231023,
             "count": 1,
-            "self": 0.019244292052462697
+            "self": 0.019822541042231023
         },
         "TrainerController.start_learning": {
-            "total": 3091.238011374953,
+            "total": 36838.163186458056,
             "count": 1,
-            "self": 0.6549470070749521,
+            "self": 5.2826125882565975,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.774538544355892,
-                    "count": 74,
-                    "self": 6.774538544355892
+                    "total": 35.27890009281691,
+                    "count": 800,
+                    "self": 35.27890009281691
                 },
                 "TrainerController.advance": {
-                    "total": 3083.530861656647,
-                    "count": 54443,
-                    "self": 0.5134963177843019,
+                    "total": 36797.39307248499,
+                    "count": 598528,
+                    "self": 4.700941964518279,
                     "children": {
                         "env_step": {
-                            "total": 2252.5134539136197,
-                            "count": 54443,
-                            "self": 2168.886104057776,
+                            "total": 24404.411351914983,
+                            "count": 598528,
+                            "self": 23575.48067614867,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 83.2792097517522,
-                                    "count": 54443,
-                                    "self": 3.171278899302706,
+                                    "total": 825.7377529452788,
+                                    "count": 598528,
+                                    "self": 32.30438491667155,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 80.1079308524495,
-                                            "count": 100012,
-                                            "self": 80.1079308524495
+                                            "total": 793.4333680286072,
+                                            "count": 1099898,
+                                            "self": 793.4333680286072
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.34814010409172624,
-                                    "count": 54443,
+                                    "total": 3.1929228210356086,
+                                    "count": 598528,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3024.2247854277957,
-                                            "count": 54443,
+                                            "total": 36683.921793210204,
+                                            "count": 598528,
                                             "is_parallel": true,
-                                            "self": 915.7552356258966,
+                                            "self": 13739.314992137952,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.10174066864419729,
-                                                    "count": 148,
+                                                    "total": 1.0775862756418064,
+                                                    "count": 1600,
                                                     "is_parallel": true,
-                                                    "self": 0.013216774677857757,
+                                                    "self": 0.13856924686115235,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.08852389396633953,
-                                                            "count": 592,
+                                                            "total": 0.9390170287806541,
+                                                            "count": 6400,
                                                             "is_parallel": true,
-                                                            "self": 0.08852389396633953
+                                                            "self": 0.9390170287806541
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2108.367809133255,
-                                                    "count": 54443,
+                                                    "total": 22943.52921479661,
+                                                    "count": 598528,
                                                     "is_parallel": true,
-                                                    "self": 5.666770220734179,
+                                                    "self": 59.51802136620972,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 40.98215689067729,
-                                                            "count": 54443,
+                                                            "total": 450.8881625722861,
+                                                            "count": 598528,
                                                             "is_parallel": true,
-                                                            "self": 40.98215689067729
+                                                            "self": 450.8881625722861
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1992.8668013456045,
-                                                            "count": 54443,
+                                                            "total": 21693.82560560596,
+                                                            "count": 598528,
                                                             "is_parallel": true,
-                                                            "self": 1992.8668013456045
+                                                            "self": 21693.82560560596
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 68.85208067623898,
-                                                            "count": 108886,
+                                                            "total": 739.2974252521526,
+                                                            "count": 1197056,
                                                             "is_parallel": true,
-                                                            "self": 8.394826258183457,
+                                                            "self": 88.14237605035305,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 60.45725441805553,
-                                                                    "count": 435544,
+                                                                    "total": 651.1550492017996,
+                                                                    "count": 4788224,
                                                                     "is_parallel": true,
-                                                                    "self": 60.45725441805553
+                                                                    "self": 651.1550492017996
                                                                 }
                                                             }
                                                         }
@@ -421,31 +421,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 830.5039114252431,
-                            "count": 54443,
-                            "self": 5.782571685384028,
+                            "total": 12388.280778605491,
+                            "count": 598528,
+                            "self": 48.189471200923435,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 163.31070186395664,
-                                    "count": 54443,
-                                    "self": 163.1295437810477,
+                                    "total": 1782.4633543648524,
+                                    "count": 598528,
+                                    "self": 1780.4024058259092,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.18115808290895075,
-                                            "count": 1,
-                                            "self": 0.18115808290895075
+                                            "total": 2.060948538943194,
+                                            "count": 16,
+                                            "self": 2.060948538943194
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 661.4106378759025,
-                                    "count": 5,
-                                    "self": 64.14400474901777,
+                                    "total": 10557.627953039715,
+                                    "count": 50,
+                                    "self": 793.9571674687322,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 597.2666331268847,
-                                            "count": 53,
-                                            "self": 597.2666331268847
+                                            "total": 9763.670785570983,
+                                            "count": 447,
+                                            "self": 9763.670785570983
                                         }
                                     }
                                 }
@@ -454,19 +454,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.5419209375977516e-06,
+                    "total": 1.00000761449337e-06,
                     "count": 1,
-                    "self": 1.5419209375977516e-06
+                    "self": 1.00000761449337e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.277662624954246,
+                    "total": 0.20860029198229313,
                     "count": 1,
-                    "self": 0.006202915916219354,
+                    "self": 0.0029710419476032257,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.27145970903802663,
+                            "total": 0.2056292500346899,
                             "count": 1,
-                            "self": 0.27145970903802663
+                            "self": 0.2056292500346899
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,24 @@
 {
     "SoccerTwos": {
-        "elo": 217.20535211320427,
+        "elo": 201.04842649379412,
         "checkpoints": [
             {
-                "steps": 137276584,
-                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-137276584.onnx",
+                "steps": 158901878,
+                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-158901878.onnx",
                 "reward": null,
-                "creation_time": 1726855117.018749,
+                "creation_time": 1726955045.165805,
                 "auxillary_file_paths": [
-                    "results/sept-run-01/SoccerTwos/SoccerTwos-137276584.pt"
+                    "results/sept-run-01/SoccerTwos/SoccerTwos-158901878.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 137276584,
+            "steps": 158901878,
             "file_path": "results/sept-run-01/SoccerTwos.onnx",
             "reward": null,
-            "creation_time": 1726855117.018749,
+            "creation_time": 1726955045.165805,
             "auxillary_file_paths": [
-                "results/sept-run-01/SoccerTwos/SoccerTwos-137276584.pt"
+                "results/sept-run-01/SoccerTwos/SoccerTwos-158901878.pt"
             ]
         }
     },