{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2798337936401367, "min": 3.2798337936401367, "max": 3.295718193054199, "count": 5 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33270.6328125, "min": 33270.6328125, "max": 105462.8828125, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 542.5714285714286, "min": 542.3333333333334, "max": 847.375, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 15192.0, "min": 13016.0, "max": 27116.0, "count": 5 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.768598826461, "min": 1200.4971269630323, "max": 1201.7051193595273, "count": 5 }, "SoccerTwos.Self-play.ELO.sum": { "value": 12007.68598826461, "min": 4801.988507852129, "max": 12007.68598826461, "count": 5 }, "SoccerTwos.Step.mean": { "value": 49048.0, "min": 9574.0, "max": 49048.0, "count": 5 }, "SoccerTwos.Step.sum": { "value": 49048.0, "min": 9574.0, "max": 49048.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.055170945823192596, "min": 0.055170945823192596, "max": 0.07871975004673004, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.8827351331710815, "min": 0.7964469790458679, "max": 1.102076530456543, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05276469513773918, "min": 0.05276469513773918, "max": 0.06743673980236053, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.8442351222038269, "min": 0.7696228623390198, "max": 0.9946800470352173, "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": -0.17647499591112137, "min": -0.3333333333333333, "max": 0.12109333674112956, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.823599934577942, "min": -4.0, "max": 1.8164000511169434, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.17647499591112137, "min": -0.3333333333333333, "max": 0.12109333674112956, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.823599934577942, "min": -4.0, "max": 1.8164000511169434, "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": 0.013646218164164262, "min": 0.013646218164164262, "max": 0.014982693060301245, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013646218164164262, "min": 0.013646218164164262, "max": 0.014982693060301245, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002452240065516283, "min": 0.002452240065516283, "max": 0.004919896406742434, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002452240065516283, "min": 0.002452240065516283, "max": 0.004919896406742434, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0025148390016208094, "min": 0.0025148390016208094, "max": 0.0044184058361376325, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0025148390016208094, "min": 0.0025148390016208094, "max": 0.0044184058361376325, "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": "1680979189", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos --run-id=SoccerTwos1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680979307" }, "total": 118.04574286399998, "count": 1, "self": 0.45058176000003414, "children": { "run_training.setup": { "total": 0.11109667099998433, "count": 1, "self": 0.11109667099998433 }, "TrainerController.start_learning": { "total": 117.48406443299996, "count": 1, "self": 0.09579972499773248, "children": { "TrainerController._reset_env": { "total": 3.975901190000002, "count": 1, "self": 3.975901190000002 }, "TrainerController.advance": { "total": 113.14286556900237, "count": 3337, "self": 0.10484734700713716, "children": { "env_step": { "total": 96.22062827399719, "count": 3337, "self": 76.29322788099887, "children": { "SubprocessEnvManager._take_step": { "total": 19.86922626699834, "count": 3337, "self": 0.6479481790017871, "children": { "TorchPolicy.evaluate": { "total": 19.221278087996552, "count": 6634, "self": 19.221278087996552 } } }, "workers": { "total": 0.05817412599998306, "count": 3337, "self": 0.0, "children": { "worker_root": { "total": 116.84212338400346, "count": 3337, "is_parallel": true, "self": 52.590282149004395, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005834853000010298, "count": 2, "is_parallel": true, "self": 0.003764468000042598, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020703849999677004, "count": 8, "is_parallel": true, "self": 0.0020703849999677004 } } }, "UnityEnvironment.step": { "total": 0.05434564199998704, "count": 1, "is_parallel": true, "self": 0.0011116820000438565, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009678319999579799, "count": 1, "is_parallel": true, "self": 0.0009678319999579799 }, "communicator.exchange": { "total": 0.0473363250000034, "count": 1, "is_parallel": true, "self": 0.0473363250000034 }, "steps_from_proto": { "total": 0.004929802999981803, "count": 2, "is_parallel": true, "self": 0.000761078000039106, "children": { "_process_rank_one_or_two_observation": { "total": 0.004168724999942697, "count": 8, "is_parallel": true, "self": 0.004168724999942697 } } } } } } }, "UnityEnvironment.step": { "total": 64.25184123499906, "count": 3336, "is_parallel": true, "self": 3.622226852001404, "children": { "UnityEnvironment._generate_step_input": { "total": 2.682477071001074, "count": 3336, "is_parallel": true, "self": 2.682477071001074 }, "communicator.exchange": { "total": 46.36657929899775, "count": 3336, "is_parallel": true, "self": 46.36657929899775 }, "steps_from_proto": { "total": 11.580558012998836, "count": 6672, "is_parallel": true, "self": 2.1652906359979625, "children": { "_process_rank_one_or_two_observation": { "total": 9.415267377000873, "count": 26688, "is_parallel": true, "self": 9.415267377000873 } } } } } } } } } } }, "trainer_advance": { "total": 16.817389947998038, "count": 3337, "self": 0.7299029829940764, "children": { "process_trajectory": { "total": 4.801076555004045, "count": 3337, "self": 4.801076555004045 }, "_update_policy": { "total": 11.286410409999917, "count": 2, "self": 6.638439132999679, "children": { "TorchPOCAOptimizer.update": { "total": 4.647971277000238, "count": 60, "self": 4.647971277000238 } } } } } } }, "trainer_threads": { "total": 9.759999102243455e-07, "count": 1, "self": 9.759999102243455e-07 }, "TrainerController._save_models": { "total": 0.2694969729999457, "count": 1, "self": 0.0019471349999093945, "children": { "RLTrainer._checkpoint": { "total": 0.2675498380000363, "count": 1, "self": 0.2675498380000363 } } } } } } }