First Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33abf63337f2ed65dd7e39237a8b2c4e25b2d5e182933577c9d174e30b9bf69
+oid sha256:e75e17c630eb15700d03b89761624b07eafd3e65504fd8ddea492326c8c8011f
 size 1764633

SoccerTwos/SoccerTwos-2794.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75e17c630eb15700d03b89761624b07eafd3e65504fd8ddea492326c8c8011f
+size 1764633

SoccerTwos/SoccerTwos-2794.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33ed152196abb0ac1e7422fa71300bacb7bcebc4d85484d46fbe5140d9dee6e
+size 9478265

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a239fb80d7d4091d1581183ede1c9e245c99bd3a13abe3882dab5f8d6f9c91aa
-size 28421137
+oid sha256:a33ed152196abb0ac1e7422fa71300bacb7bcebc4d85484d46fbe5140d9dee6e
+size 9478265

SoccerTwos/events.out.tfevents.1686748708.d37089838a3f.6889.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2725adab92e59e7bfc546cb5e461117961ce54d42e7062f013a33c9651a72316
+size 1240

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "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": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "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": false, "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: 50000
+    max_steps: 5000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.719 seconds
+- Completed reload, in  0.874 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)
@@ -56,36 +56,16 @@ 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: 1.110830 ms
+UnloadTime: 0.896118 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 1 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]: 1153 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 235 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
@@ -207,16 +187,16 @@ 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]: 1154 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 236 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.7 MB
+      Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1154 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 236 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
@@ -245,13 +225,13 @@ 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]: 1153 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 235 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]: 1154 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 236 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -263,16 +243,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 1154 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 236 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]: 1153 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 235 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -281,13 +261,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1154 frames
+      Peak usage frame count: [0-1.0 KB]: 236 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]: 1153 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 235 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

@@ -1,202 +1,8 @@
 {
     "name": "root",
-    "gauges": {
-        "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.28265643119812,
-            "min": 3.28265643119812,
-            "max": 3.295696258544922,
-            "count": 5
-        },
-        "SoccerTwos.Policy.Entropy.sum": {
-            "value": 88763.03125,
-            "min": 29053.037109375,
-            "max": 105462.21875,
-            "count": 5
-        },
-        "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 754.6666666666666,
-            "min": 668.3333333333334,
-            "max": 820.1666666666666,
-            "count": 5
-        },
-        "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 18112.0,
-            "min": 16040.0,
-            "max": 25180.0,
-            "count": 5
-        },
-        "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1198.3874877821277,
-            "min": 1198.0911687838272,
-            "max": 1201.004267761486,
-            "count": 5
-        },
-        "SoccerTwos.Self-play.ELO.sum": {
-            "value": 4793.549951128511,
-            "min": 4793.549951128511,
-            "max": 9608.034142091888,
-            "count": 5
-        },
-        "SoccerTwos.Step.mean": {
-            "value": 49926.0,
-            "min": 9608.0,
-            "max": 49926.0,
-            "count": 5
-        },
-        "SoccerTwos.Step.sum": {
-            "value": 49926.0,
-            "min": 9608.0,
-            "max": 49926.0,
-            "count": 5
-        },
-        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.06536506116390228,
-            "min": 0.06536506116390228,
-            "max": 0.10138500481843948,
-            "count": 5
-        },
-        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.8497458100318909,
-            "min": 0.8497458100318909,
-            "max": 1.5207037925720215,
-            "count": 5
-        },
-        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.06429646909236908,
-            "min": 0.06429646909236908,
-            "max": 0.10138337314128876,
-            "count": 5
-        },
-        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.8358541131019592,
-            "min": 0.8358541131019592,
-            "max": 1.520679235458374,
-            "count": 5
-        },
-        "SoccerTwos.Environment.CumulativeReward.mean": {
-            "value": 0.0,
-            "min": 0.0,
-            "max": 0.0,
-            "count": 5
-        },
-        "SoccerTwos.Environment.CumulativeReward.sum": {
-            "value": 0.0,
-            "min": 0.0,
-            "max": 0.0,
-            "count": 5
-        },
-        "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.04378461837768555,
-            "min": -0.25,
-            "max": -0.04378461837768555,
-            "count": 5
-        },
-        "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -0.5692000389099121,
-            "min": -3.0648000240325928,
-            "max": -0.5692000389099121,
-            "count": 5
-        },
-        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.04378461837768555,
-            "min": -0.25,
-            "max": -0.04378461837768555,
-            "count": 5
-        },
-        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -0.5692000389099121,
-            "min": -3.0648000240325928,
-            "max": -0.5692000389099121,
-            "count": 5
-        },
-        "SoccerTwos.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 5
-        },
-        "SoccerTwos.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 5
-        },
-        "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.018575048559190083,
-            "min": 0.018208359370085723,
-            "max": 0.018575048559190083,
-            "count": 2
-        },
-        "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.018575048559190083,
-            "min": 0.018208359370085723,
-            "max": 0.018575048559190083,
-            "count": 2
-        },
-        "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.004095277213491499,
-            "min": 0.004095277213491499,
-            "max": 0.005249080806970596,
-            "count": 2
-        },
-        "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.004095277213491499,
-            "min": 0.004095277213491499,
-            "max": 0.005249080806970596,
-            "count": 2
-        },
-        "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0041288621801262105,
-            "min": 0.0041288621801262105,
-            "max": 0.004664750932715833,
-            "count": 2
-        },
-        "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0041288621801262105,
-            "min": 0.0041288621801262105,
-            "max": 0.004664750932715833,
-            "count": 2
-        },
-        "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 2
-        },
-        "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 2
-        },
-        "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.20000000000000007,
-            "min": 0.20000000000000007,
-            "max": 0.20000000000000007,
-            "count": 2
-        },
-        "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.20000000000000007,
-            "min": 0.20000000000000007,
-            "max": 0.20000000000000007,
-            "count": 2
-        },
-        "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
-            "max": 0.005000000000000001,
-            "count": 2
-        },
-        "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
-            "max": 0.005000000000000001,
-            "count": 2
-        }
-    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1686748280",
+        "start_time_seconds": "1686748705",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics",
         "mlagents_version": "0.31.0.dev0",
@@ -204,59 +10,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1686748587"
+        "end_time_seconds": "1686748738"
     },
-    "total": 306.415053358,
+    "total": 33.052970894000055,
     "count": 1,
-    "self": 1.121778402000018,
+    "self": 0.33947862600007284,
     "children": {
         "run_training.setup": {
-            "total": 0.0938294400000359,
+            "total": 0.06832204300008016,
             "count": 1,
-            "self": 0.0938294400000359
+            "self": 0.06832204300008016
         },
         "TrainerController.start_learning": {
-            "total": 305.19944551599997,
+            "total": 32.6451702249999,
             "count": 1,
-            "self": 0.15516480800101817,
+            "self": 0.030823673994973433,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.553870785000072,
+                    "total": 2.2724867280001035,
                     "count": 1,
-                    "self": 2.553870785000072
+                    "self": 2.2724867280001035
                 },
                 "TrainerController.advance": {
-                    "total": 301.9086998829989,
-                    "count": 3860,
-                    "self": 0.16292576999762787,
+                    "total": 29.596817908004823,
+                    "count": 786,
+                    "self": 0.03293174200621252,
                     "children": {
                         "env_step": {
-                            "total": 135.97904770200284,
-                            "count": 3860,
-                            "self": 111.68265270400366,
+                            "total": 27.952460072998974,
+                            "count": 786,
+                            "self": 23.146774284001367,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 24.206270759996187,
-                                    "count": 3860,
-                                    "self": 0.9830231650059886,
+                                    "total": 4.788731201000019,
+                                    "count": 786,
+                                    "self": 0.2026699519972226,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 23.223247594990198,
-                                            "count": 7690,
-                                            "self": 23.223247594990198
+                                            "total": 4.586061249002796,
+                                            "count": 1568,
+                                            "self": 4.586061249002796
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.09012423800299985,
-                                    "count": 3860,
+                                    "total": 0.016954587997588533,
+                                    "count": 785,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 302.3054157560109,
-                                            "count": 3860,
+                                            "total": 31.7358276460011,
+                                            "count": 785,
                                             "is_parallel": true,
-                                            "self": 209.07813883900644,
+                                            "self": 12.433781939002301,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +71,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.004979842000011558,
+                                                            "total": 0.004423301000088031,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.001133596999807196,
+                                                            "self": 0.0011540060006609565,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0038462450002043624,
+                                                                    "total": 0.003269294999427075,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0038462450002043624
+                                                                    "self": 0.003269294999427075
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07906042300010085,
+                                                            "total": 0.05084969499989711,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0013764720001745445,
+                                                            "self": 0.0013758599998254795,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0010573090000889351,
+                                                                    "total": 0.0011552159999155265,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0010573090000889351
+                                                                    "self": 0.0011552159999155265
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.07225851399994099,
+                                                                    "total": 0.04405214700000215,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.07225851399994099
+                                                                    "self": 0.04405214700000215
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.004368127999896387,
+                                                                    "total": 0.0042664720001539536,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008362700000361656,
+                                                                    "self": 0.0008813620002001699,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0035318579998602218,
+                                                                            "total": 0.0033851099999537837,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0035318579998602218
+                                                                            "self": 0.0033851099999537837
                                                                         }
                                                                     }
                                                                 }
@@ -315,34 +121,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 93.22727691700447,
-                                                    "count": 3859,
+                                                    "total": 19.302045706998797,
+                                                    "count": 784,
                                                     "is_parallel": true,
-                                                    "self": 5.486070685996538,
+                                                    "self": 1.1347571000064818,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.933011493001686,
-                                                            "count": 3859,
+                                                            "total": 0.6015711309985363,
+                                                            "count": 784,
                                                             "is_parallel": true,
-                                                            "self": 2.933011493001686
+                                                            "self": 0.6015711309985363
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 67.80359328600025,
-                                                            "count": 3859,
+                                                            "total": 13.988910074998785,
+                                                            "count": 784,
                                                             "is_parallel": true,
-                                                            "self": 67.80359328600025
+                                                            "self": 13.988910074998785
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 17.004601452006,
-                                                            "count": 7718,
+                                                            "total": 3.576807400994994,
+                                                            "count": 1568,
                                                             "is_parallel": true,
-                                                            "self": 3.028566120012556,
+                                                            "self": 0.6389004019983986,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 13.976035331993444,
-                                                                    "count": 30872,
+                                                                    "total": 2.9379069989965956,
+                                                                    "count": 6272,
                                                                     "is_parallel": true,
-                                                                    "self": 13.976035331993444
+                                                                    "self": 2.9379069989965956
                                                                 }
                                                             }
                                                         }
@@ -355,45 +161,33 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 165.76672641099844,
-                            "count": 3860,
-                            "self": 0.9075624519957728,
+                            "total": 1.6114260929996362,
+                            "count": 785,
+                            "self": 0.10081051099723481,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 22.190596382002468,
-                                    "count": 3860,
-                                    "self": 22.190596382002468
-                                },
-                                "_update_policy": {
-                                    "total": 142.6685675770002,
-                                    "count": 2,
-                                    "self": 10.168901357000323,
-                                    "children": {
-                                        "TorchPOCAOptimizer.update": {
-                                            "total": 132.49966621999988,
-                                            "count": 60,
-                                            "self": 132.49966621999988
-                                        }
-                                    }
+                                    "total": 1.5106155820024014,
+                                    "count": 785,
+                                    "self": 1.5106155820024014
                                 }
                             }
                         }
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.6999999843392288e-06,
+                    "total": 1.94700010069937e-06,
                     "count": 1,
-                    "self": 1.6999999843392288e-06
+                    "self": 1.94700010069937e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.5817083399999774,
+                    "total": 0.7450399679999009,
                     "count": 1,
-                    "self": 0.01770135299989306,
+                    "self": 0.02608699899997191,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.5640069870000843,
+                            "total": 0.718952968999929,
                             "count": 1,
-                            "self": 0.5640069870000843
+                            "self": 0.718952968999929
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,24 @@
 {
     "SoccerTwos": {
-        "elo": 1199.0185606756888,
+        "elo": 1200.9928540150988,
         "checkpoints": [
             {
-                "steps": 51926,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-51926.onnx",
+                "steps": 2794,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2794.onnx",
                 "reward": 0.0,
-                "creation_time": 1686748585.8895307,
+                "creation_time": 1686748738.4783692,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-51926.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2794.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 51926,
+            "steps": 2794,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1686748585.8895307,
+            "creation_time": 1686748738.4783692,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-51926.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-2794.pt"
             ]
         }
     },