{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6733875274658203, "min": 1.54535973072052, "max": 3.2957680225372314, "count": 1015 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32932.265625, "min": 24784.818359375, "max": 110003.34375, "count": 1015 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.28358208955224, "min": 38.944, "max": 999.0, "count": 1015 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 9896.0, "max": 30272.0, "count": 1015 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1604.4913136163316, "min": 1197.9636370809403, "max": 1644.5692666973036, "count": 1010 }, "SoccerTwos.Self-play.ELO.sum": { "value": 215001.83602458844, "min": 2399.954394668513, "max": 383071.48428452644, "count": 1010 }, "SoccerTwos.Step.mean": { "value": 10149998.0, "min": 9154.0, "max": 10149998.0, "count": 1015 }, "SoccerTwos.Step.sum": { "value": 10149998.0, "min": 9154.0, "max": 10149998.0, "count": 1015 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.033328767865896225, "min": -0.13804522156715393, "max": 0.16708561778068542, "count": 1015 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.499383449554443, "min": -27.747089385986328, "max": 22.533878326416016, "count": 1015 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.027855442836880684, "min": -0.13877856731414795, "max": 0.1622379869222641, "count": 1015 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.7604846954345703, "min": -27.894493103027344, "max": 22.18732452392578, "count": 1015 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1015 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1015 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.17867555529982956, "min": -0.7402066648006439, "max": 0.42132572191102163, "count": 1015 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -24.12119996547699, "min": -61.86719971895218, "max": 68.27119982242584, "count": 1015 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.17867555529982956, "min": -0.7402066648006439, "max": 0.42132572191102163, "count": 1015 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -24.12119996547699, "min": -61.86719971895218, "max": 68.27119982242584, "count": 1015 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1015 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1015 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017461659600182127, "min": 0.010983511048834771, "max": 0.02463465513549939, "count": 490 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017461659600182127, "min": 0.010983511048834771, "max": 0.02463465513549939, "count": 490 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10232649942239126, "min": 0.00012617104875971562, "max": 0.12690836166342098, "count": 490 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10232649942239126, "min": 0.00012617104875971562, "max": 0.12690836166342098, "count": 490 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10372459217905998, "min": 0.0001274863961346758, "max": 0.12863116388519605, "count": 490 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10372459217905998, "min": 0.0001274863961346758, "max": 0.12863116388519605, "count": 490 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 490 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 490 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 490 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 490 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 490 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 490 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697010939", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/pratiksahu/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1697038329" }, "total": 27390.272950756997, "count": 1, "self": 0.12002200999631896, "children": { "run_training.setup": { "total": 0.01260914500016952, "count": 1, "self": 0.01260914500016952 }, "TrainerController.start_learning": { "total": 27390.140319602, "count": 1, "self": 16.053767128374602, "children": { "TrainerController._reset_env": { "total": 2.6578026099859926, "count": 51, "self": 2.6578026099859926 }, "TrainerController.advance": { "total": 27371.28318441563, "count": 699595, "self": 16.338328312976955, "children": { "env_step": { "total": 13453.082639340362, "count": 699595, "self": 10998.26593173443, "children": { "SubprocessEnvManager._take_step": { "total": 2445.015888093034, "count": 699595, "self": 87.34362612423956, "children": { "TorchPolicy.evaluate": { "total": 2357.6722619687944, "count": 1278194, "self": 2357.6722619687944 } } }, "workers": { "total": 9.80081951289958, "count": 699595, "self": 0.0, "children": { "worker_root": { "total": 27356.016303455872, "count": 699595, "is_parallel": true, "self": 18123.262498261232, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00869886599957681, "count": 2, "is_parallel": true, "self": 0.0008132769999065204, "children": { "_process_rank_one_or_two_observation": { "total": 0.00788558899967029, "count": 8, "is_parallel": true, "self": 0.00788558899967029 } } }, "UnityEnvironment.step": { "total": 0.028004748999592266, "count": 1, "is_parallel": true, "self": 0.0010529580004003947, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009929059997375589, "count": 1, "is_parallel": true, "self": 0.0009929059997375589 }, "communicator.exchange": { "total": 0.023819101999833947, "count": 1, "is_parallel": true, "self": 0.023819101999833947 }, "steps_from_proto": { "total": 0.0021397829996203654, "count": 2, "is_parallel": true, "self": 0.0004454340005395352, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016943489990808303, "count": 8, "is_parallel": true, "self": 0.0016943489990808303 } } } } } } }, "UnityEnvironment.step": { "total": 9232.659042750625, "count": 699594, "is_parallel": true, "self": 617.3098799673953, "children": { "UnityEnvironment._generate_step_input": { "total": 517.3478126689351, "count": 699594, "is_parallel": true, "self": 517.3478126689351 }, "communicator.exchange": { "total": 6598.871512075196, "count": 699594, "is_parallel": true, "self": 6598.871512075196 }, "steps_from_proto": { "total": 1499.1298380391, "count": 1399188, "is_parallel": true, "self": 267.4946303377519, "children": { "_process_rank_one_or_two_observation": { "total": 1231.635207701348, "count": 5596752, "is_parallel": true, "self": 1231.635207701348 } } } } }, "steps_from_proto": { "total": 0.09476244401503209, "count": 100, "is_parallel": true, "self": 0.017355094018967065, "children": { "_process_rank_one_or_two_observation": { "total": 0.07740734999606502, "count": 400, "is_parallel": true, "self": 0.07740734999606502 } } } } } } } } }, "trainer_advance": { "total": 13901.862216762293, "count": 699595, "self": 123.82960816949708, "children": { "process_trajectory": { "total": 2435.25220416478, "count": 699595, "self": 2432.5660685357834, "children": { "RLTrainer._checkpoint": { "total": 2.6861356289964533, "count": 20, "self": 2.6861356289964533 } } }, "_update_policy": { "total": 11342.780404428015, "count": 491, "self": 1579.338189706019, "children": { "TorchPOCAOptimizer.update": { "total": 9763.442214721996, "count": 14717, "self": 9763.442214721996 } } } } } } }, "trainer_threads": { "total": 1.0120056685991585e-06, "count": 1, "self": 1.0120056685991585e-06 }, "TrainerController._save_models": { "total": 0.14556443600304192, "count": 1, "self": 0.0013899430050514638, "children": { "RLTrainer._checkpoint": { "total": 0.14417449299799046, "count": 1, "self": 0.14417449299799046 } } } } } } }