7.2 million steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8350e4d18979f950861a009550af4c3b015bd79ac0ed3043fecac6d074566f4e
+oid sha256:0dfdcbd2d042799047b90538be44081922e976dbf3875030ca1b6d84561cec75
 size 2815689

SoccerTwos/{SoccerTwos-5428910.onnx → SoccerTwos-7040162.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6a82e9c437f162e433d8a71cd87868b6e3518ab8827487158b0d6632e306c9
+oid sha256:8350e4d18979f950861a009550af4c3b015bd79ac0ed3043fecac6d074566f4e
 size 2815689

SoccerTwos/{SoccerTwos-5428910.pt → SoccerTwos-7040162.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6bf53b8a41e2f4e2288b5a8b8fbd140092c09f97c1a475c20dad6cf09fc0ef8
+oid sha256:e93e08eef37f0d2e32b962ed9deedcd8f162da3cb33e23cfbefbd0b7589fddeb
 size 34728689

SoccerTwos/{SoccerTwos-5999918.onnx → SoccerTwos-7228646.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9639a06fd270b742cbd0268bf7f8e3a4e449b8d59e52321d672403e9f054a8a
+oid sha256:0dfdcbd2d042799047b90538be44081922e976dbf3875030ca1b6d84561cec75
 size 2815689

SoccerTwos/{SoccerTwos-5999918.pt → SoccerTwos-7228646.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c666f122e8fb532d6c584866e1869efd6406a2a8ba1386722263946f0b94684e
+oid sha256:5816573f4baa92d72950deb45e726fc0c48d013fb7be1ecc5269ec7335b6c5f0
 size 34728689

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490f419786244d154ec9fc97f7e0b3734afdfb764a70e9af573cb87a0a36ed1c
+oid sha256:5816573f4baa92d72950deb45e726fc0c48d013fb7be1ecc5269ec7335b6c5f0
 size 34728689

SoccerTwos/events.out.tfevents.1683492142.CLM-FVFF611QQ05P.local.62005.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc4f346062a29ba8788dce1da49a00790a0f70f7f30abd9b4a54a51ed2147c6
+size 21464

SoccerTwos/events.out.tfevents.1683492229.CLM-FVFF611QQ05P.local.63367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7f9abc1109b726341bd6c36bae15a5983f13e55966caaa916f728ab883380b
+size 185992

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 2000000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.973, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 2000, "window": 50, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 2000000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.973, "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": 15000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 2000, "window": 50, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 10000000
+    max_steps: 15000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -10,7 +10,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.079 seconds
+- Completed reload, in  0.076 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)
@@ -35,16 +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: 1.122042 ms
+UnloadTime: 1.420500 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-Thread 0x16c7e7000 may have been prematurely finalized
+Thread 0x171477000 may have been prematurely finalized
 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]: 8797 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 3543 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
@@ -87,7 +87,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
@@ -102,7 +102,7 @@ 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
@@ -195,22 +195,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 2
+  Peak main deferred allocation count 3
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 8798 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 3544 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.8 MB
+      Peak Allocated memory 5.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 8798 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 3544 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 MB
+      Peak Allocated memory 17.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -239,13 +239,13 @@ 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]: 8797 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3543 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]: 8798 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 3544 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -257,13 +257,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 8798 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 3544 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]: 8797 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 3543 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
@@ -275,13 +275,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 8798 frames
+      Peak usage frame count: [0-1.0 KB]: 3544 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]: 8797 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 3543 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": 2.5312271118164062,
-            "min": 2.4752397537231445,
-            "max": 2.6057534217834473,
-            "count": 47
+            "value": 2.5318515300750732,
+            "min": 2.5223515033721924,
+            "max": 2.5813586711883545,
+            "count": 18
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 50219.546875,
-            "min": 27830.3125,
-            "max": 57770.609375,
-            "count": 47
+            "value": 49259.703125,
+            "min": 47095.140625,
+            "max": 53957.95703125,
+            "count": 18
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 61.73076923076923,
-            "min": 52.10752688172043,
-            "max": 80.63934426229508,
-            "count": 47
+            "value": 56.67816091954023,
+            "min": 54.18681318681319,
+            "max": 76.01538461538462,
+            "count": 18
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19260.0,
-            "min": 9148.0,
-            "max": 20936.0,
-            "count": 47
+            "value": 19724.0,
+            "min": 19148.0,
+            "max": 20264.0,
+            "count": 18
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1655.8477577114181,
-            "min": 1630.1141578570837,
-            "max": 1672.5534725499353,
-            "count": 47
+            "value": 1679.7317393981489,
+            "min": 1656.1921875095022,
+            "max": 1679.7317393981489,
+            "count": 18
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 258312.25020298123,
-            "min": 122544.41556046242,
-            "max": 306301.84157527966,
-            "count": 47
+            "value": 292273.3226552779,
+            "min": 215649.28115044435,
+            "max": 305145.5088457796,
+            "count": 18
         },
         "SoccerTwos.Step.mean": {
-            "value": 7019974.0,
-            "min": 6559966.0,
-            "max": 7019974.0,
-            "count": 47
+            "value": 7219992.0,
+            "min": 7049887.0,
+            "max": 7219992.0,
+            "count": 18
         },
         "SoccerTwos.Step.sum": {
-            "value": 7019974.0,
-            "min": 6559966.0,
-            "max": 7019974.0,
-            "count": 47
+            "value": 7219992.0,
+            "min": 7049887.0,
+            "max": 7219992.0,
+            "count": 18
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.0246932040899992,
-            "min": -0.07469330728054047,
-            "max": 0.06775432825088501,
-            "count": 47
+            "value": 0.008738174103200436,
+            "min": -0.07982506603002548,
+            "max": 0.008738174103200436,
+            "count": 18
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -3.852139949798584,
-            "min": -11.428075790405273,
-            "max": 9.824377059936523,
-            "count": 47
+            "value": 1.520442247390747,
+            "min": -12.13340950012207,
+            "max": 1.520442247390747,
+            "count": 18
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.025697926059365273,
-            "min": -0.07545823603868484,
-            "max": 0.06745122373104095,
-            "count": 47
+            "value": 0.009255587123334408,
+            "min": -0.0813833549618721,
+            "max": 0.009255587123334408,
+            "count": 18
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -4.008876323699951,
-            "min": -11.545109748840332,
-            "max": 9.780427932739258,
-            "count": 47
+            "value": 1.6104722023010254,
+            "min": -12.370269775390625,
+            "max": 1.6104722023010254,
+            "count": 18
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 47
+            "count": 18
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 47
+            "count": 18
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.06588461383795127,
-            "min": -0.2788773345947266,
-            "max": 0.22914206899445633,
-            "count": 47
+            "value": 0.1608482739706149,
+            "min": -0.20066532969474793,
+            "max": 0.1608482739706149,
+            "count": 18
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 10.277999758720398,
-            "min": -41.831600189208984,
-            "max": 33.22560000419617,
-            "count": 47
+            "value": 27.987599670886993,
+            "min": -33.53679966926575,
+            "max": 27.987599670886993,
+            "count": 18
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.06588461383795127,
-            "min": -0.2788773345947266,
-            "max": 0.22914206899445633,
-            "count": 47
+            "value": 0.1608482739706149,
+            "min": -0.20066532969474793,
+            "max": 0.1608482739706149,
+            "count": 18
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 10.277999758720398,
-            "min": -41.831600189208984,
-            "max": 33.22560000419617,
-            "count": 47
+            "value": 27.987599670886993,
+            "min": -33.53679966926575,
+            "max": 27.987599670886993,
+            "count": 18
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 47
+            "count": 18
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 47
+            "count": 18
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.014652803967085978,
-            "min": 0.01367914140234158,
-            "max": 0.0207417576079024,
-            "count": 22
+            "value": 0.016063779070585347,
+            "min": 0.015077678242232651,
+            "max": 0.02123676067761456,
+            "count": 8
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.014652803967085978,
-            "min": 0.01367914140234158,
-            "max": 0.0207417576079024,
-            "count": 22
+            "value": 0.016063779070585347,
+            "min": 0.015077678242232651,
+            "max": 0.02123676067761456,
+            "count": 8
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.06511050388216973,
-            "min": 0.054490877439578374,
-            "max": 0.0683522641658783,
-            "count": 22
+            "value": 0.06546799217661221,
+            "min": 0.06479480353494485,
+            "max": 0.06966093542675177,
+            "count": 8
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.06511050388216973,
-            "min": 0.054490877439578374,
-            "max": 0.0683522641658783,
-            "count": 22
+            "value": 0.06546799217661221,
+            "min": 0.06479480353494485,
+            "max": 0.06966093542675177,
+            "count": 8
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.06548771560192108,
-            "min": 0.05498399945596854,
-            "max": 0.06909144831200441,
-            "count": 22
+            "value": 0.06590312644839287,
+            "min": 0.0653505644450585,
+            "max": 0.07026846731702487,
+            "count": 8
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.06548771560192108,
-            "min": 0.05498399945596854,
-            "max": 0.06909144831200441,
-            "count": 22
+            "value": 0.06590312644839287,
+            "min": 0.0653505644450585,
+            "max": 0.07026846731702487,
+            "count": 8
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.00019999999999999996,
             "min": 0.00019999999999999996,
             "max": 0.00019999999999999996,
-            "count": 22
+            "count": 8
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.00019999999999999996,
             "min": 0.00019999999999999996,
             "max": 0.00019999999999999996,
-            "count": 22
+            "count": 8
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 22
+            "count": 8
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 22
+            "count": 8
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 22
+            "count": 8
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 22
+            "count": 8
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1683489403",
+        "start_time_seconds": "1683492227",
         "python_version": "3.9.16 | packaged by conda-forge | (main, Feb  1 2023, 21:38:11) \n[Clang 14.0.6 ]",
         "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
@@ -204,103 +204,103 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1683491523"
+        "end_time_seconds": "1683493071"
     },
-    "total": 2120.7075272919997,
+    "total": 843.9403655000001,
     "count": 1,
-    "self": 0.11400120799953584,
+    "self": 0.14983404100019015,
     "children": {
         "run_training.setup": {
-            "total": 0.013764458999999896,
+            "total": 0.023452833999999978,
             "count": 1,
-            "self": 0.013764458999999896
+            "self": 0.023452833999999978
         },
         "TrainerController.start_learning": {
-            "total": 2120.579761625,
+            "total": 843.767078625,
             "count": 1,
-            "self": 0.39264614000012443,
+            "self": 0.15948642700573146,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.9952624579999387,
-                    "count": 4,
-                    "self": 1.9952624579999387
+                    "total": 1.5302018339999996,
+                    "count": 2,
+                    "self": 1.5302018339999996
                 },
                 "TrainerController.advance": {
-                    "total": 2118.0091342349997,
-                    "count": 32174,
-                    "self": 0.3491077030012093,
+                    "total": 841.9261699059942,
+                    "count": 13040,
+                    "self": 0.13282511599504687,
                     "children": {
                         "env_step": {
-                            "total": 1698.4356740170083,
-                            "count": 32174,
-                            "self": 1638.031515376033,
+                            "total": 681.1283580699985,
+                            "count": 13040,
+                            "self": 657.7465356490007,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 60.13042827897286,
-                                    "count": 32174,
-                                    "self": 1.4789845239499186,
+                                    "total": 23.280398930000096,
+                                    "count": 13040,
+                                    "self": 0.6736503810056327,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 58.65144375502294,
-                                            "count": 58650,
-                                            "self": 58.65144375502294
+                                            "total": 22.606748548994464,
+                                            "count": 23622,
+                                            "self": 22.606748548994464
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.27373036200252665,
-                                    "count": 32173,
+                                    "total": 0.10142349099767767,
+                                    "count": 13039,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2117.892491209032,
-                                            "count": 32173,
+                                            "total": 841.8678021200012,
+                                            "count": 13039,
                                             "is_parallel": true,
-                                            "self": 529.1141985200231,
+                                            "self": 202.98945657000388,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.006709541000275099,
-                                                    "count": 8,
+                                                    "total": 0.0034942079999997766,
+                                                    "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.0007980410003163296,
+                                                    "self": 0.0004312480000001617,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.005911499999958769,
-                                                            "count": 32,
+                                                            "total": 0.003062959999999615,
+                                                            "count": 16,
                                                             "is_parallel": true,
-                                                            "self": 0.005911499999958769
+                                                            "self": 0.003062959999999615
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1588.7715831480086,
-                                                    "count": 32173,
+                                                    "total": 638.8748513419973,
+                                                    "count": 13039,
                                                     "is_parallel": true,
-                                                    "self": 4.106521291980243,
+                                                    "self": 1.6371326879955177,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 28.195529624995782,
-                                                            "count": 32173,
+                                                            "total": 11.2325981490038,
+                                                            "count": 13039,
                                                             "is_parallel": true,
-                                                            "self": 28.195529624995782
+                                                            "self": 11.2325981490038
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1497.7160278380102,
-                                                            "count": 32173,
+                                                            "total": 602.5734008570001,
+                                                            "count": 13039,
                                                             "is_parallel": true,
-                                                            "self": 1497.7160278380102
+                                                            "self": 602.5734008570001
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 58.75350439302243,
-                                                            "count": 64346,
+                                                            "total": 23.431719647997838,
+                                                            "count": 26078,
                                                             "is_parallel": true,
-                                                            "self": 6.588014732984448,
+                                                            "self": 2.6071703399854265,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 52.165489660037984,
-                                                                    "count": 257384,
+                                                                    "total": 20.82454930801241,
+                                                                    "count": 104312,
                                                                     "is_parallel": true,
-                                                                    "self": 52.165489660037984
+                                                                    "self": 20.82454930801241
                                                                 }
                                                             }
                                                         }
@@ -313,24 +313,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 419.22435251499024,
-                            "count": 32173,
-                            "self": 2.6727334479645606,
+                            "total": 160.6649867200007,
+                            "count": 13039,
+                            "self": 1.0906056580058987,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 91.07927935702565,
-                                    "count": 32173,
-                                    "self": 91.07927935702565
+                                    "total": 32.77911264699492,
+                                    "count": 13039,
+                                    "self": 32.77911264699492
                                 },
                                 "_update_policy": {
-                                    "total": 325.47233971,
-                                    "count": 22,
-                                    "self": 40.14159451100102,
+                                    "total": 126.79526841499991,
+                                    "count": 9,
+                                    "self": 15.891884914000315,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 285.330745198999,
-                                            "count": 660,
-                                            "self": 285.330745198999
+                                            "total": 110.9033835009996,
+                                            "count": 270,
+                                            "self": 110.9033835009996
                                         }
                                     }
                                 }
@@ -339,19 +339,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.420001798484009e-07,
+                    "total": 6.24999984211172e-07,
                     "count": 1,
-                    "self": 5.420001798484009e-07
+                    "self": 6.24999984211172e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.18271825000010722,
+                    "total": 0.1512198330000274,
                     "count": 1,
-                    "self": 0.000976583000010578,
+                    "self": 0.0007593750000296495,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18174166700009664,
+                            "total": 0.15046045799999774,
                             "count": 1,
-                            "self": 0.18174166700009664
+                            "self": 0.15046045799999774
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,25 +1,7 @@
 {
     "SoccerTwos": {
-        "elo": 1664.046005142632,
+        "elo": 1685.0464592105432,
         "checkpoints": [
-            {
-                "steps": 5428910,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5428910.onnx",
-                "reward": 0.0,
-                "creation_time": 1683430502.922749,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5428910.pt"
-                ]
-            },
-            {
-                "steps": 5999918,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5999918.onnx",
-                "reward": 0.0,
-                "creation_time": 1683486797.098654,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5999918.pt"
-                ]
-            },
             {
                 "steps": 6187920,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6187920.onnx",
@@ -46,15 +28,33 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-7021752.pt"
                 ]
+            },
+            {
+                "steps": 7040162,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7040162.onnx",
+                "reward": 0.0,
+                "creation_time": 1683492216.468576,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7040162.pt"
+                ]
+            },
+            {
+                "steps": 7228646,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7228646.onnx",
+                "reward": 0.0,
+                "creation_time": 1683493071.7239301,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7228646.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 7021752,
+            "steps": 7228646,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1683491523.676715,
+            "creation_time": 1683493071.7239301,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-7021752.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-7228646.pt"
             ]
         }
     },