{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2807910442352295, "min": 3.2807910442352295, "max": 3.295742988586426, "count": 5 }, "SoccerTwos.Policy.Entropy.sum": { "value": 84723.1484375, "min": 51235.0546875, "max": 105463.7734375, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 955.4, "min": 745.2, "max": 999.0, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19108.0, "min": 14904.0, "max": 25888.0, "count": 5 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.2960463941354, "min": 1198.2960463941354, "max": 1199.4207269131573, "count": 4 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2396.5920927882707, "min": 2396.5920927882707, "max": 7196.524361478944, "count": 4 }, "SoccerTwos.Step.mean": { "value": 49974.0, "min": 9960.0, "max": 49974.0, "count": 5 }, "SoccerTwos.Step.sum": { "value": 49974.0, "min": 9960.0, "max": 49974.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06636136025190353, "min": -0.07005516439676285, "max": -0.06636136025190353, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.7299749255180359, "min": -0.9106462597846985, "max": -0.6965510845184326, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06056693568825722, "min": -0.07001491636037827, "max": -0.06056693568825722, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.6662362813949585, "min": -0.9100764989852905, "max": -0.6329516172409058, "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": -0.18181818181818182, "min": -0.3241333334396283, "max": 0.001360000018030405, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -3.8896000012755394, "max": 0.01360000018030405, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.18181818181818182, "min": -0.3241333334396283, "max": 0.001360000018030405, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -3.8896000012755394, "max": 0.01360000018030405, "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": 0.01809350042991961, "min": 0.017385530701075267, "max": 0.01809350042991961, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01809350042991961, "min": 0.017385530701075267, "max": 0.01809350042991961, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0007348242984638394, "min": 0.0007348242984638394, "max": 0.002954561379738152, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0007348242984638394, "min": 0.0007348242984638394, "max": 0.002954561379738152, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0007452838452688108, "min": 0.0007452838452688108, "max": 0.002745604452987512, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0007452838452688108, "min": 0.0007452838452688108, "max": 0.002745604452987512, "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": 0.20000000000000004, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "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": "1683590226", "python_version": "3.9.13 (main, Jul 20 2022, 22:20:50) \n[GCC 11.3.0]", "command_line_arguments": "/home/thekeymaster/Server/Projects/Hugging-Face-Course/Unit-7-AI-vs-AI/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1683590430" }, "total": 204.44136967899976, "count": 1, "self": 1.05795118399692, "children": { "run_training.setup": { "total": 0.10620303400173725, "count": 1, "self": 0.10620303400173725 }, "TrainerController.start_learning": { "total": 203.2772154610011, "count": 1, "self": 0.11539166511465737, "children": { "TrainerController._reset_env": { "total": 42.49264526099978, "count": 1, "self": 42.49264526099978 }, "TrainerController.advance": { "total": 153.98561443488506, "count": 3819, "self": 0.11292492894426687, "children": { "env_step": { "total": 126.35035360599795, "count": 3819, "self": 104.39870043693008, "children": { "SubprocessEnvManager._take_step": { "total": 21.879080556025656, "count": 3819, "self": 0.6794282059963734, "children": { "TorchPolicy.evaluate": { "total": 21.199652350029282, "count": 7614, "self": 21.199652350029282 } } }, "workers": { "total": 0.07257261304221174, "count": 3819, "self": 0.0, "children": { "worker_root": { "total": 196.03046066292882, "count": 3819, "is_parallel": true, "self": 108.00857298397568, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.021005970000260277, "count": 2, "is_parallel": true, "self": 0.015773913997691125, "children": { "_process_rank_one_or_two_observation": { "total": 0.005232056002569152, "count": 8, "is_parallel": true, "self": 0.005232056002569152 } } }, "UnityEnvironment.step": { "total": 0.03804310700070346, "count": 1, "is_parallel": true, "self": 0.000784120000389521, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0015876180004852358, "count": 1, "is_parallel": true, "self": 0.0015876180004852358 }, "communicator.exchange": { "total": 0.0332690930008539, "count": 1, "is_parallel": true, "self": 0.0332690930008539 }, "steps_from_proto": { "total": 0.002402275998974801, "count": 2, "is_parallel": true, "self": 0.0004890790005447343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019131969984300667, "count": 8, "is_parallel": true, "self": 0.0019131969984300667 } } } } } } }, "UnityEnvironment.step": { "total": 88.02188767895314, "count": 3818, "is_parallel": true, "self": 5.955326958886872, "children": { "UnityEnvironment._generate_step_input": { "total": 4.789865059981821, "count": 3818, "is_parallel": true, "self": 4.789865059981821 }, "communicator.exchange": { "total": 58.98325425498115, "count": 3818, "is_parallel": true, "self": 58.98325425498115 }, "steps_from_proto": { "total": 18.293441405103295, "count": 7636, "is_parallel": true, "self": 3.5349990402028197, "children": { "_process_rank_one_or_two_observation": { "total": 14.758442364900475, "count": 30544, "is_parallel": true, "self": 14.758442364900475 } } } } } } } } } } }, "trainer_advance": { "total": 27.522335899942846, "count": 3819, "self": 1.270590202879248, "children": { "process_trajectory": { "total": 7.35048717706195, "count": 3819, "self": 7.35048717706195 }, "_update_policy": { "total": 18.901258520001647, "count": 2, "self": 14.493343388008725, "children": { "TorchPOCAOptimizer.update": { "total": 4.407915131992922, "count": 66, "self": 4.407915131992922 } } } } } } }, "trainer_threads": { "total": 1.6730009519960731e-06, "count": 1, "self": 1.6730009519960731e-06 }, "TrainerController._save_models": { "total": 6.683562427000652, "count": 1, "self": 0.22492797700033407, "children": { "RLTrainer._checkpoint": { "total": 6.458634450000318, "count": 1, "self": 6.458634450000318 } } } } } } }