7 million steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938451bcaff44acbe51f407c436b7194c2536f33414a46d8c63a8ec4ebef6e4c
+oid sha256:8350e4d18979f950861a009550af4c3b015bd79ac0ed3043fecac6d074566f4e
 size 2815689

SoccerTwos/{SoccerTwos-3999978.onnx → SoccerTwos-7021752.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464bafac7a238220c28da578ce08118b3c5d8546fa2d2f4a1bfa3c611f04ecaa
+oid sha256:8350e4d18979f950861a009550af4c3b015bd79ac0ed3043fecac6d074566f4e
 size 2815689

SoccerTwos/{SoccerTwos-3999978.pt → SoccerTwos-7021752.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13608f7ec5f0ea0552ccea43730bb4a730ee87c74633190c89655fba948c5302
+oid sha256:490f419786244d154ec9fc97f7e0b3734afdfb764a70e9af573cb87a0a36ed1c
 size 34728689

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b24686f444a9a2ee6005e0fd0ff7cd1e4f3675c1c6be7372b906f496a971669
+oid sha256:490f419786244d154ec9fc97f7e0b3734afdfb764a70e9af573cb87a0a36ed1c
 size 34728689

SoccerTwos/events.out.tfevents.1683489404.CLM-FVFF611QQ05P.local.19018.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65113e1790b6696cfdbfa62d0c3bdb4cdc606bb81853af2201a541b69aace53e
+size 484026

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.00025, "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": 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}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.00025
+      learning_rate: 0.0002
       beta: 0.01
       epsilon: 0.25
       lambd: 0.95

run_logs/Player-0.log

@@ -10,7 +10,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.097 seconds
+- Completed reload, in  0.079 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: 1.679917 ms
+UnloadTime: 1.122042 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-Thread 0x16e6df000 may have been prematurely finalized
+Thread 0x16c7e7000 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]: 6919 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 8797 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
@@ -72,7 +72,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       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_Background Job.Worker 10]
       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 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
@@ -201,16 +201,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 6920 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 8798 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.0 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]: 6920 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8798 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.5 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]: 6919 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8797 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]: 6920 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 8798 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]: 6920 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 8798 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]: 6919 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 8797 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]: 6920 frames
+      Peak usage frame count: [0-1.0 KB]: 8798 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]: 6919 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 8797 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": 2.503404140472412,
-            "min": 2.4523873329162598,
-            "max": 2.5370821952819824,
-            "count": 37
+            "value": 2.5312271118164062,
+            "min": 2.4752397537231445,
+            "max": 2.6057534217834473,
+            "count": 47
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 47905.140625,
-            "min": 16055.9697265625,
-            "max": 55159.47265625,
-            "count": 37
+            "value": 50219.546875,
+            "min": 27830.3125,
+            "max": 57770.609375,
+            "count": 47
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 64.93333333333334,
-            "min": 49.91752577319588,
-            "max": 76.84375,
-            "count": 37
+            "value": 61.73076923076923,
+            "min": 52.10752688172043,
+            "max": 80.63934426229508,
+            "count": 47
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19480.0,
-            "min": 4772.0,
-            "max": 20184.0,
-            "count": 37
+            "value": 19260.0,
+            "min": 9148.0,
+            "max": 20936.0,
+            "count": 47
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1652.4748588887048,
-            "min": 1642.8951631352754,
-            "max": 1669.7917318437467,
-            "count": 37
+            "value": 1655.8477577114181,
+            "min": 1630.1141578570837,
+            "max": 1672.5534725499353,
+            "count": 47
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 247871.2288333057,
-            "min": 76077.51671093542,
-            "max": 321056.13316160464,
-            "count": 37
+            "value": 258312.25020298123,
+            "min": 122544.41556046242,
+            "max": 306301.84157527966,
+            "count": 47
         },
         "SoccerTwos.Step.mean": {
-            "value": 6549982.0,
-            "min": 6189948.0,
-            "max": 6549982.0,
-            "count": 37
+            "value": 7019974.0,
+            "min": 6559966.0,
+            "max": 7019974.0,
+            "count": 47
         },
         "SoccerTwos.Step.sum": {
-            "value": 6549982.0,
-            "min": 6189948.0,
-            "max": 6549982.0,
-            "count": 37
+            "value": 7019974.0,
+            "min": 6559966.0,
+            "max": 7019974.0,
+            "count": 47
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.051142871379852295,
-            "min": -0.06000871956348419,
-            "max": 0.0756918340921402,
-            "count": 37
+            "value": -0.0246932040899992,
+            "min": -0.07469330728054047,
+            "max": 0.06775432825088501,
+            "count": 47
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 7.671430587768555,
-            "min": -9.386945724487305,
-            "max": 12.262077331542969,
-            "count": 37
+            "value": -3.852139949798584,
+            "min": -11.428075790405273,
+            "max": 9.824377059936523,
+            "count": 47
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.05099420249462128,
-            "min": -0.05922776460647583,
-            "max": 0.07353535294532776,
-            "count": 37
+            "value": -0.025697926059365273,
+            "min": -0.07545823603868484,
+            "max": 0.06745122373104095,
+            "count": 47
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 7.649130344390869,
-            "min": -9.559730529785156,
-            "max": 11.912727355957031,
-            "count": 37
+            "value": -4.008876323699951,
+            "min": -11.545109748840332,
+            "max": 9.780427932739258,
+            "count": 47
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 37
+            "count": 47
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 37
+            "count": 47
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.07690666834513346,
-            "min": -0.2579976199638276,
-            "max": 0.22876027267273158,
-            "count": 37
+            "value": 0.06588461383795127,
+            "min": -0.2788773345947266,
+            "max": 0.22914206899445633,
+            "count": 47
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 11.53600025177002,
-            "min": -43.343600153923035,
-            "max": 35.7960000038147,
-            "count": 37
+            "value": 10.277999758720398,
+            "min": -41.831600189208984,
+            "max": 33.22560000419617,
+            "count": 47
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.07690666834513346,
-            "min": -0.2579976199638276,
-            "max": 0.22876027267273158,
-            "count": 37
+            "value": 0.06588461383795127,
+            "min": -0.2788773345947266,
+            "max": 0.22914206899445633,
+            "count": 47
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 11.53600025177002,
-            "min": -43.343600153923035,
-            "max": 35.7960000038147,
-            "count": 37
+            "value": 10.277999758720398,
+            "min": -41.831600189208984,
+            "max": 33.22560000419617,
+            "count": 47
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 37
+            "count": 47
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 37
+            "count": 47
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.013742929190630093,
-            "min": 0.013162332853729216,
-            "max": 0.021872061599666873,
-            "count": 17
+            "value": 0.014652803967085978,
+            "min": 0.01367914140234158,
+            "max": 0.0207417576079024,
+            "count": 22
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.013742929190630093,
-            "min": 0.013162332853729216,
-            "max": 0.021872061599666873,
-            "count": 17
+            "value": 0.014652803967085978,
+            "min": 0.01367914140234158,
+            "max": 0.0207417576079024,
+            "count": 22
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.060539432987570765,
-            "min": 0.05456341157356898,
-            "max": 0.06828681615491708,
-            "count": 17
+            "value": 0.06511050388216973,
+            "min": 0.054490877439578374,
+            "max": 0.0683522641658783,
+            "count": 22
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.060539432987570765,
-            "min": 0.05456341157356898,
-            "max": 0.06828681615491708,
-            "count": 17
+            "value": 0.06511050388216973,
+            "min": 0.054490877439578374,
+            "max": 0.0683522641658783,
+            "count": 22
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.06114285662770271,
-            "min": 0.05531582894424598,
-            "max": 0.0692600845048825,
-            "count": 17
+            "value": 0.06548771560192108,
+            "min": 0.05498399945596854,
+            "max": 0.06909144831200441,
+            "count": 22
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.06114285662770271,
-            "min": 0.05531582894424598,
-            "max": 0.0692600845048825,
-            "count": 17
+            "value": 0.06548771560192108,
+            "min": 0.05498399945596854,
+            "max": 0.06909144831200441,
+            "count": 22
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.00025000000000000006,
-            "min": 0.00025000000000000006,
-            "max": 0.00025000000000000006,
-            "count": 17
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 22
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.00025000000000000006,
-            "min": 0.00025000000000000006,
-            "max": 0.00025000000000000006,
-            "count": 17
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 22
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 17
+            "count": 22
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 17
+            "count": 22
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 17
+            "count": 22
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 17
+            "count": 22
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1683487709",
+        "start_time_seconds": "1683489403",
         "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": "1683489353"
+        "end_time_seconds": "1683491523"
     },
-    "total": 1643.169040458,
+    "total": 2120.7075272919997,
     "count": 1,
-    "self": 0.11722787500002596,
+    "self": 0.11400120799953584,
     "children": {
         "run_training.setup": {
-            "total": 0.013663792000000008,
+            "total": 0.013764458999999896,
             "count": 1,
-            "self": 0.013663792000000008
+            "self": 0.013764458999999896
         },
         "TrainerController.start_learning": {
-            "total": 1643.038148791,
+            "total": 2120.579761625,
             "count": 1,
-            "self": 0.31101058200579246,
+            "self": 0.39264614000012443,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2248240839999744,
-                    "count": 3,
-                    "self": 2.2248240839999744
+                    "total": 1.9952624579999387,
+                    "count": 4,
+                    "self": 1.9952624579999387
                 },
                 "TrainerController.advance": {
-                    "total": 1640.320858083994,
-                    "count": 25389,
-                    "self": 0.2661743909673078,
+                    "total": 2118.0091342349997,
+                    "count": 32174,
+                    "self": 0.3491077030012093,
                     "children": {
                         "env_step": {
-                            "total": 1330.830156340017,
-                            "count": 25389,
-                            "self": 1284.3852757490256,
+                            "total": 1698.4356740170083,
+                            "count": 32174,
+                            "self": 1638.031515376033,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 46.23812745699054,
-                                    "count": 25389,
-                                    "self": 1.2487462569900671,
+                                    "total": 60.13042827897286,
+                                    "count": 32174,
+                                    "self": 1.4789845239499186,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 44.98938120000047,
-                                            "count": 46132,
-                                            "self": 44.98938120000047
+                                            "total": 58.65144375502294,
+                                            "count": 58650,
+                                            "self": 58.65144375502294
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.20675313400085837,
-                                    "count": 25388,
+                                    "total": 0.27373036200252665,
+                                    "count": 32173,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1640.2869981199963,
-                                            "count": 25388,
+                                            "total": 2117.892491209032,
+                                            "count": 32173,
                                             "is_parallel": true,
-                                            "self": 393.89563319499894,
+                                            "self": 529.1141985200231,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.005132874999992598,
-                                                    "count": 6,
+                                                    "total": 0.006709541000275099,
+                                                    "count": 8,
                                                     "is_parallel": true,
-                                                    "self": 0.0006161679999161507,
+                                                    "self": 0.0007980410003163296,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0045167070000764475,
-                                                            "count": 24,
+                                                            "total": 0.005911499999958769,
+                                                            "count": 32,
                                                             "is_parallel": true,
-                                                            "self": 0.0045167070000764475
+                                                            "self": 0.005911499999958769
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1246.3862320499973,
-                                                    "count": 25388,
+                                                    "total": 1588.7715831480086,
+                                                    "count": 32173,
                                                     "is_parallel": true,
-                                                    "self": 3.1823133230072926,
+                                                    "self": 4.106521291980243,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.304695663003482,
-                                                            "count": 25388,
+                                                            "total": 28.195529624995782,
+                                                            "count": 32173,
                                                             "is_parallel": true,
-                                                            "self": 22.304695663003482
+                                                            "self": 28.195529624995782
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1175.0904308869885,
-                                                            "count": 25388,
+                                                            "total": 1497.7160278380102,
+                                                            "count": 32173,
                                                             "is_parallel": true,
-                                                            "self": 1175.0904308869885
+                                                            "self": 1497.7160278380102
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 45.808792176997834,
-                                                            "count": 50776,
+                                                            "total": 58.75350439302243,
+                                                            "count": 64346,
                                                             "is_parallel": true,
-                                                            "self": 5.091343413956125,
+                                                            "self": 6.588014732984448,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 40.71744876304171,
-                                                                    "count": 203104,
+                                                                    "total": 52.165489660037984,
+                                                                    "count": 257384,
                                                                     "is_parallel": true,
-                                                                    "self": 40.71744876304171
+                                                                    "self": 52.165489660037984
                                                                 }
                                                             }
                                                         }
@@ -313,24 +313,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 309.2245273530094,
-                            "count": 25388,
-                            "self": 2.159055672025943,
+                            "total": 419.22435251499024,
+                            "count": 32173,
+                            "self": 2.6727334479645606,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 68.22423439098337,
-                                    "count": 25388,
-                                    "self": 68.22423439098337
+                                    "total": 91.07927935702565,
+                                    "count": 32173,
+                                    "self": 91.07927935702565
                                 },
                                 "_update_policy": {
-                                    "total": 238.8412372900001,
-                                    "count": 17,
-                                    "self": 29.788104290999627,
+                                    "total": 325.47233971,
+                                    "count": 22,
+                                    "self": 40.14159451100102,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 209.05313299900047,
-                                            "count": 510,
-                                            "self": 209.05313299900047
+                                            "total": 285.330745198999,
+                                            "count": 660,
+                                            "self": 285.330745198999
                                         }
                                     }
                                 }
@@ -339,19 +339,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.1600014810683206e-07,
+                    "total": 5.420001798484009e-07,
                     "count": 1,
-                    "self": 4.1600014810683206e-07
+                    "self": 5.420001798484009e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.18145562500012602,
+                    "total": 0.18271825000010722,
                     "count": 1,
-                    "self": 0.0011100420001639577,
+                    "self": 0.000976583000010578,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18034558299996206,
+                            "total": 0.18174166700009664,
                             "count": 1,
-                            "self": 0.18034558299996206
+                            "self": 0.18174166700009664
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,16 +1,7 @@
 {
     "SoccerTwos": {
-        "elo": 1655.486498013031,
+        "elo": 1664.046005142632,
         "checkpoints": [
-            {
-                "steps": 3999978,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999978.onnx",
-                "reward": 0.0,
-                "creation_time": 1683424087.475253,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999978.pt"
-                ]
-            },
             {
                 "steps": 5428910,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5428910.onnx",
@@ -46,15 +37,24 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-6555492.pt"
                 ]
+            },
+            {
+                "steps": 7021752,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7021752.onnx",
+                "reward": 0.0,
+                "creation_time": 1683491523.676715,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7021752.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 6555492,
+            "steps": 7021752,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1683489352.9770849,
+            "creation_time": 1683491523.676715,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-6555492.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-7021752.pt"
             ]
         }
     },