{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.60512113571167, "min": 2.576058864593506, "max": 3.2957584857940674, "count": 153 }, "SoccerTwos.Policy.Entropy.sum": { "value": 49768.234375, "min": 19701.3984375, "max": 105464.1875, "count": 153 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.44285714285714, "min": 55.69318181818182, "max": 999.0, "count": 153 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 16380.0, "max": 25536.0, "count": 153 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1432.0507427110429, "min": 1198.9900907842039, "max": 1439.0801697786028, "count": 152 }, "SoccerTwos.Self-play.ELO.sum": { "value": 200487.103979546, "min": 2397.9801815684077, "max": 245331.37821920833, "count": 152 }, "SoccerTwos.Step.mean": { "value": 1529960.0, "min": 9786.0, "max": 1529960.0, "count": 153 }, "SoccerTwos.Step.sum": { "value": 1529960.0, "min": 9786.0, "max": 1529960.0, "count": 153 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.08859968930482864, "min": -0.03122873045504093, "max": 0.25784891843795776, "count": 153 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 12.315357208251953, "min": -4.340793609619141, "max": 26.724498748779297, "count": 153 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.07361045479774475, "min": -0.03681948408484459, "max": 0.25843432545661926, "count": 153 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 10.231853485107422, "min": -5.117908477783203, "max": 25.840808868408203, "count": 153 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 153 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 153 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.12326043329650549, "min": -0.5714285714285714, "max": 0.6532827560929046, "count": 153 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 17.133200228214264, "min": -21.79960000514984, "max": 56.8355997800827, "count": 153 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.12326043329650549, "min": -0.5714285714285714, "max": 0.6532827560929046, "count": 153 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 17.133200228214264, "min": -21.79960000514984, "max": 56.8355997800827, "count": 153 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 153 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 153 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017969103282666765, "min": 0.010487537668571653, "max": 0.021603452736356606, "count": 72 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017969103282666765, "min": 0.010487537668571653, "max": 0.021603452736356606, "count": 72 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08188363139828046, "min": 0.0016951362524802486, "max": 0.08501399084925651, "count": 72 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08188363139828046, "min": 0.0016951362524802486, "max": 0.08501399084925651, "count": 72 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08477470974127452, "min": 0.0017042422861171266, "max": 0.08773589010039966, "count": 72 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08477470974127452, "min": 0.0017042422861171266, "max": 0.08773589010039966, "count": 72 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 72 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 72 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 72 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 72 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 72 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 72 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716284271", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\ASUSROG\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1716295092" }, "total": 10820.996979999938, "count": 1, "self": 1.0817919998662546, "children": { "run_training.setup": { "total": 0.2845190000953153, "count": 1, "self": 0.2845190000953153 }, "TrainerController.start_learning": { "total": 10819.630668999976, "count": 1, "self": 7.065667584189214, "children": { "TrainerController._reset_env": { "total": 21.102362099918537, "count": 8, "self": 21.102362099918537 }, "TrainerController.advance": { "total": 10791.088720715838, "count": 101527, "self": 7.374858103692532, "children": { "env_step": { "total": 5743.239232376101, "count": 101527, "self": 4415.3459142574575, "children": { "SubprocessEnvManager._take_step": { "total": 1323.189395701862, "count": 101527, "self": 43.19361850025598, "children": { "TorchPolicy.evaluate": { "total": 1279.995777201606, "count": 195294, "self": 1279.995777201606 } } }, "workers": { "total": 4.703922416782007, "count": 101527, "self": 0.0, "children": { "worker_root": { "total": 10749.106660613208, "count": 101527, "is_parallel": true, "self": 7286.344790431438, "children": { "steps_from_proto": { "total": 0.04099139990285039, "count": 16, "is_parallel": true, "self": 0.00800789927598089, "children": { "_process_rank_one_or_two_observation": { "total": 0.0329835006268695, "count": 64, "is_parallel": true, "self": 0.0329835006268695 } } }, "UnityEnvironment.step": { "total": 3462.720878781867, "count": 101527, "is_parallel": true, "self": 200.90259891434107, "children": { "UnityEnvironment._generate_step_input": { "total": 198.3468875954859, "count": 101527, "is_parallel": true, "self": 198.3468875954859 }, "communicator.exchange": { "total": 2370.8362009989796, "count": 101527, "is_parallel": true, "self": 2370.8362009989796 }, "steps_from_proto": { "total": 692.6351912730606, "count": 203054, "is_parallel": true, "self": 133.0821683453396, "children": { "_process_rank_one_or_two_observation": { "total": 559.553022927721, "count": 812216, "is_parallel": true, "self": 559.553022927721 } } } } } } } } } } }, "trainer_advance": { "total": 5040.474630236044, "count": 101527, "self": 41.68894123204518, "children": { "process_trajectory": { "total": 1336.936692404328, "count": 101527, "self": 1335.9088755045086, "children": { "RLTrainer._checkpoint": { "total": 1.0278168998192996, "count": 3, "self": 1.0278168998192996 } } }, "_update_policy": { "total": 3661.8489965996705, "count": 73, "self": 485.0931242010556, "children": { "TorchPOCAOptimizer.update": { "total": 3176.755872398615, "count": 2186, "self": 3176.755872398615 } } } } } } }, "trainer_threads": { "total": 3.100023604929447e-06, "count": 1, "self": 3.100023604929447e-06 }, "TrainerController._save_models": { "total": 0.3739155000075698, "count": 1, "self": 0.016544800018891692, "children": { "RLTrainer._checkpoint": { "total": 0.3573706999886781, "count": 1, "self": 0.3573706999886781 } } } } } } }