Corrected_agent

SoccerTwos/events.out.tfevents.1691587294.5d3260be6dee.5217.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afdcf8a9c0c501b70310b180515e3c0e31cb3466456e85c00bc16cc2d2b52e6
+size 83161

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.975, "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": 17000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.975, "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": 20000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 17000000
+    max_steps: 20000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(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  0.164 seconds
+- Completed reload, in  0.110 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)
@@ -56,7 +56,7 @@ 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: 1.113635 ms
+UnloadTime: 1.021965 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
@@ -65,7 +65,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 1569 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
@@ -181,19 +181,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 2
     [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]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1570 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.5 MB
+      Peak Allocated memory 4.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1570 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.6 MB
@@ -210,7 +210,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -225,13 +225,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1569 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]: 1 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 1570 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -243,13 +243,13 @@ 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]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 1570 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: [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 1569 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.5 MB
@@ -261,13 +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]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 1570 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: [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1569 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

@@ -1,8 +1,202 @@
 {
     "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.9658901691436768,
+            "min": 1.9507466554641724,
+            "max": 2.012911319732666,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 41959.9609375,
+            "min": 35585.39453125,
+            "max": 42420.859375,
+            "count": 8
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 55.92045454545455,
+            "min": 52.40625,
+            "max": 69.42028985507247,
+            "count": 8
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19684.0,
+            "min": 19124.0,
+            "max": 20124.0,
+            "count": 8
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1538.4805800913457,
+            "min": 1531.2502836486121,
+            "max": 1551.3227554528323,
+            "count": 8
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 270772.58209607686,
+            "min": 211814.58659889572,
+            "max": 294000.05446053355,
+            "count": 8
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 17079943.0,
+            "min": 17009908.0,
+            "max": 17079943.0,
+            "count": 8
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 17079943.0,
+            "min": 17009908.0,
+            "max": 17079943.0,
+            "count": 8
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.02461826801300049,
+            "min": -0.048662248998880386,
+            "max": 0.02817954123020172,
+            "count": 8
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -4.332815170288086,
+            "min": -6.764052391052246,
+            "max": 5.044137954711914,
+            "count": 8
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.026582615450024605,
+            "min": -0.04911984130740166,
+            "max": 0.029571032151579857,
+            "count": 8
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -4.678540229797363,
+            "min": -6.827658176422119,
+            "max": 5.293214797973633,
+            "count": 8
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 8
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 8
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.10118636387315663,
+            "min": -0.2481161294444915,
+            "max": 0.14639768779622336,
+            "count": 8
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 17.808800041675568,
+            "min": -38.45800006389618,
+            "max": 25.326799988746643,
+            "count": 8
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.10118636387315663,
+            "min": -0.2481161294444915,
+            "max": 0.14639768779622336,
+            "count": 8
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 17.808800041675568,
+            "min": -38.45800006389618,
+            "max": 25.326799988746643,
+            "count": 8
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017275884848398468,
+            "min": 0.01401178379698346,
+            "max": 0.017275884848398468,
+            "count": 3
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017275884848398468,
+            "min": 0.01401178379698346,
+            "max": 0.017275884848398468,
+            "count": 3
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.1466987907886505,
+            "min": 0.1420595775047938,
+            "max": 0.14836741834878922,
+            "count": 3
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.1466987907886505,
+            "min": 0.1420595775047938,
+            "max": 0.14836741834878922,
+            "count": 3
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.14792554477850597,
+            "min": 0.14344171136617662,
+            "max": 0.14968455731868743,
+            "count": 3
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.14792554477850597,
+            "min": 0.14344171136617662,
+            "max": 0.14968455731868743,
+            "count": 3
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 3
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 3
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 3
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 3
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 3
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 3
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691502651",
+        "start_time_seconds": "1691587293",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu",
         "mlagents_version": "0.31.0.dev0",
@@ -10,41 +204,210 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1691502653"
+        "end_time_seconds": "1691587671"
     },
-    "total": 2.346567974000209,
+    "total": 377.5817969909999,
     "count": 1,
-    "self": 0.591593690000991,
+    "self": 0.6829773079998631,
     "children": {
         "run_training.setup": {
-            "total": 0.088049349999892,
+            "total": 0.050948197000025175,
             "count": 1,
-            "self": 0.088049349999892
+            "self": 0.050948197000025175
         },
         "TrainerController.start_learning": {
-            "total": 1.6669249339993257,
+            "total": 376.84787148600003,
             "count": 1,
-            "self": 0.000251513999501185,
+            "self": 0.2890012780030702,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.415294059000189,
-                    "count": 1,
-                    "self": 1.415294059000189
+                    "total": 1.3325371700000233,
+                    "count": 2,
+                    "self": 1.3325371700000233
+                },
+                "TrainerController.advance": {
+                    "total": 375.2259686049972,
+                    "count": 5783,
+                    "self": 0.3135287849904671,
+                    "children": {
+                        "env_step": {
+                            "total": 211.60110524900642,
+                            "count": 5783,
+                            "self": 177.79245621000632,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 33.646761729993386,
+                                    "count": 5783,
+                                    "self": 1.7361510119956165,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 31.91061071799777,
+                                            "count": 10466,
+                                            "self": 31.91061071799777
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.16188730900671544,
+                                    "count": 5782,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 374.13457776899304,
+                                            "count": 5782,
+                                            "is_parallel": true,
+                                            "self": 227.5943619929842,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0041112719998182,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.001114076999556346,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002997195000261854,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002997195000261854
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04913036999982978,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0015919759998723748,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.001028115000053731,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001028115000053731
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.041588480999962485,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.041588480999962485
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.004921797999941191,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0009275249999518564,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0039942729999893345,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0039942729999893345
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.0025606240001252445,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.0005008770003769314,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.002059746999748313,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.002059746999748313
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 146.5376551520087,
+                                                    "count": 5781,
+                                                    "is_parallel": true,
+                                                    "self": 8.55501642400759,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 4.43151189900118,
+                                                            "count": 5781,
+                                                            "is_parallel": true,
+                                                            "self": 4.43151189900118
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 106.6782809889994,
+                                                            "count": 5781,
+                                                            "is_parallel": true,
+                                                            "self": 106.6782809889994
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 26.872845840000537,
+                                                            "count": 11562,
+                                                            "is_parallel": true,
+                                                            "self": 4.9421501299798365,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 21.9306957100207,
+                                                                    "count": 46248,
+                                                                    "is_parallel": true,
+                                                                    "self": 21.9306957100207
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 163.31133457100032,
+                            "count": 5782,
+                            "self": 2.0864497099976234,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 34.70503600100278,
+                                    "count": 5782,
+                                    "self": 34.70503600100278
+                                },
+                                "_update_policy": {
+                                    "total": 126.51984885999991,
+                                    "count": 4,
+                                    "self": 22.335070173997792,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 104.18477868600212,
+                                            "count": 120,
+                                            "self": 104.18477868600212
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 1.258999873243738e-06,
+                    "total": 1.8829998680303106e-06,
                     "count": 1,
-                    "self": 1.258999873243738e-06
+                    "self": 1.8829998680303106e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.2513781019997623,
+                    "total": 0.0003625499998634041,
                     "count": 1,
-                    "self": 0.0015739059999759775,
+                    "self": 7.700899982410192e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.24980419599978632,
+                            "total": 0.00028554100003930216,
                             "count": 1,
-                            "self": 0.24980419599978632
+                            "self": 0.00028554100003930216
                         }
                     }
                 }

run_logs/training_status.json

@@ -47,7 +47,7 @@
                 ]
             }
         ],
-        "elo": 1534.3333126847701,
+        "elo": 1544.3301474540472,
         "final_checkpoint": {
             "steps": 17000414,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",