{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.182288408279419, "min": 3.0933775901794434, "max": 3.220071315765381, "count": 576 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46945.1171875, "min": 16037.2646484375, "max": 136210.59375, "count": 576 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 884.6666666666666, "min": 413.0, "max": 999.0, "count": 576 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21232.0, "min": 4124.0, "max": 32224.0, "count": 576 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 579 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 579 }, "SoccerTwos.Step.mean": { "value": 6279706.0, "min": 509918.0, "max": 6279706.0, "count": 578 }, "SoccerTwos.Step.sum": { "value": 6279706.0, "min": 509918.0, "max": 6279706.0, "count": 578 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01396675780415535, "min": -0.05658244341611862, "max": 0.016231367364525795, "count": 578 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.1676010936498642, "min": -0.5658244490623474, "max": 0.17637597024440765, "count": 578 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.014062275178730488, "min": -0.055558525025844574, "max": 0.015311190858483315, "count": 578 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.16874730587005615, "min": -0.5555852651596069, "max": 0.16713017225265503, "count": 578 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 578 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 578 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.23516666640837988, "min": -0.7619047619047619, "max": 0.348853333791097, "count": 578 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.8219999969005585, "min": -16.0, "max": 5.232800006866455, "count": 578 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.23516666640837988, "min": -0.7619047619047619, "max": 0.348853333791097, "count": 578 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.8219999969005585, "min": -16.0, "max": 5.232800006866455, "count": 578 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1182.101386411086, "min": 1181.715351512748, "max": 1208.3098518066217, "count": 401 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4728.405545644344, "min": 2363.430703025496, "max": 19114.790807949634, "count": 401 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014128632230131189, "min": 0.010590878160049519, "max": 0.025718933763952616, "count": 268 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014128632230131189, "min": 0.010590878160049519, "max": 0.025718933763952616, "count": 268 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0015891821162464718, "min": 1.1867135185639199e-07, "max": 0.007879177434369921, "count": 268 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0015891821162464718, "min": 1.1867135185639199e-07, "max": 0.007879177434369921, "count": 268 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0015895014454144984, "min": 1.1291880023615401e-07, "max": 0.008019201923161745, "count": 268 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0015895014454144984, "min": 1.1291880023615401e-07, "max": 0.008019201923161745, "count": 268 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 268 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 268 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 268 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 268 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 268 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 268 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679263052", "python_version": "3.9.9 (tags/v3.9.9:ccb0e6a, Nov 15 2021, 18:08:50) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "d:\\TrainingNew\\HuggingFace\\ml-agents\\.venv\\Scripts\\mlagents-learn D:\\TrainingNew\\HuggingFace\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=D:\\TrainingNew\\HuggingFace\\ml-agents\\trained-envs-executables\\Windows\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.19.0", "end_time_seconds": "1679277160" }, "total": 14109.1429318, "count": 1, "self": 0.1645528999997623, "children": { "run_training.setup": { "total": 0.0829571, "count": 1, "self": 0.0829571 }, "TrainerController.start_learning": { "total": 14108.8954218, "count": 1, "self": 6.972521100056838, "children": { "TrainerController._reset_env": { "total": 5.142922300001633, "count": 30, "self": 5.142922300001633 }, "TrainerController.advance": { "total": 14096.65730339994, "count": 375522, "self": 6.707203600128196, "children": { "env_step": { "total": 5861.249589899942, "count": 375522, "self": 4639.451646799965, "children": { "SubprocessEnvManager._take_step": { "total": 1217.3133767004051, "count": 375522, "self": 38.24895090057203, "children": { "TorchPolicy.evaluate": { "total": 1179.064425799833, "count": 745798, "self": 186.65692750003666, "children": { "TorchPolicy.sample_actions": { "total": 992.4074982997964, "count": 745798, "self": 992.4074982997964 } } } } }, "workers": { "total": 4.484566399572321, "count": 375522, "self": 0.0, "children": { "worker_root": { "total": 14094.906482399021, "count": 375522, "is_parallel": true, "self": 10297.78115999844, "children": { "steps_from_proto": { "total": 0.06598950000970305, "count": 60, "is_parallel": true, "self": 0.009468900014045989, "children": { "_process_rank_one_or_two_observation": { "total": 0.05652059999565706, "count": 240, "is_parallel": true, "self": 0.05652059999565706 } } }, "UnityEnvironment.step": { "total": 3797.059332900572, "count": 375522, "is_parallel": true, "self": 161.0923635002623, "children": { "UnityEnvironment._generate_step_input": { "total": 124.6826580000654, "count": 375522, "is_parallel": true, "self": 124.6826580000654 }, "communicator.exchange": { "total": 2684.421011100283, "count": 375522, "is_parallel": true, "self": 2684.421011100283 }, "steps_from_proto": { "total": 826.8633002999613, "count": 751044, "is_parallel": true, "self": 113.35586109928875, "children": { "_process_rank_one_or_two_observation": { "total": 713.5074392006726, "count": 3004176, "is_parallel": true, "self": 713.5074392006726 } } } } } } } } } } }, "trainer_advance": { "total": 8228.700509899869, "count": 375522, "self": 54.51821760027724, "children": { "process_trajectory": { "total": 1203.310642599593, "count": 375522, "self": 1201.518963799596, "children": { "RLTrainer._checkpoint": { "total": 1.7916787999970438, "count": 12, "self": 1.7916787999970438 } } }, "_update_policy": { "total": 6970.871649699999, "count": 268, "self": 850.3078800000085, "children": { "TorchPOCAOptimizer.update": { "total": 6120.56376969999, "count": 8067, "self": 6120.56376969999 } } } } } } }, "trainer_threads": { "total": 3.300001480965875e-06, "count": 1, "self": 3.300001480965875e-06 }, "TrainerController._save_models": { "total": 0.1226717000008648, "count": 1, "self": 0.002498100000593695, "children": { "RLTrainer._checkpoint": { "total": 0.12017360000027111, "count": 1, "self": 0.12017360000027111 } } } } } } }