{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8448234796524048, "min": 1.7827210426330566, "max": 3.2957472801208496, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38667.5, "min": 21874.908203125, "max": 118266.96875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.18681318681319, "min": 40.608333333333334, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20088.0, "min": 16308.0, "max": 24156.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1638.9551668867218, "min": 1196.3703374214208, "max": 1643.7267323121498, "count": 498 }, "SoccerTwos.Self-play.ELO.sum": { "value": 298289.84037338337, "min": 2394.524918640403, "max": 376242.54906729347, "count": 498 }, "SoccerTwos.Step.mean": { "value": 4999860.0, "min": 9096.0, "max": 4999860.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999860.0, "min": 9096.0, "max": 4999860.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04752557352185249, "min": -0.10519690066576004, "max": 0.17328228056430817, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 8.649654388427734, "min": -18.59147071838379, "max": 35.273250579833984, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0490778312087059, "min": -0.10707984119653702, "max": 0.17463314533233643, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.932165145874023, "min": -19.95433807373047, "max": 35.5179443359375, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.015215383781181587, "min": -0.7706000000238419, "max": 0.4468805193901062, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.769199848175049, "min": -61.963199973106384, "max": 64.50340002775192, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.015215383781181587, "min": -0.7706000000238419, "max": 0.4468805193901062, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.769199848175049, "min": -61.963199973106384, "max": 64.50340002775192, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018510479600323985, "min": 0.00921370624046176, "max": 0.02436254124622792, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018510479600323985, "min": 0.00921370624046176, "max": 0.02436254124622792, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10518327032526334, "min": 0.0008564350117618839, "max": 0.1266746498644352, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10518327032526334, "min": 0.0008564350117618839, "max": 0.1266746498644352, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10649096717437108, "min": 0.0008512460762479652, "max": 0.12907827720046045, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10649096717437108, "min": 0.0008512460762479652, "max": 0.12907827720046045, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716801003", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/media/fast/code/learning/venv_learning/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716806378" }, "total": 5374.680278655025, "count": 1, "self": 0.3679984110640362, "children": { "run_training.setup": { "total": 0.14300561393611133, "count": 1, "self": 0.14300561393611133 }, "TrainerController.start_learning": { "total": 5374.169274630025, "count": 1, "self": 4.976561686838977, "children": { "TrainerController._reset_env": { "total": 5.110102920443751, "count": 25, "self": 5.110102920443751 }, "TrainerController.advance": { "total": 5363.987556022825, "count": 344357, "self": 4.974061955930665, "children": { "env_step": { "total": 4113.432212984189, "count": 344357, "self": 2906.255522805848, "children": { "SubprocessEnvManager._take_step": { "total": 1203.8607318192953, "count": 344357, "self": 26.547632063971832, "children": { "TorchPolicy.evaluate": { "total": 1177.3130997553235, "count": 629108, "self": 1177.3130997553235 } } }, "workers": { "total": 3.315958359045908, "count": 344357, "self": 0.0, "children": { "worker_root": { "total": 5367.593900271109, "count": 344357, "is_parallel": true, "self": 2978.264871275518, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013673820067197084, "count": 2, "is_parallel": true, "self": 0.0003451470984145999, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010222349083051085, "count": 8, "is_parallel": true, "self": 0.0010222349083051085 } } }, "UnityEnvironment.step": { "total": 0.014498173026368022, "count": 1, "is_parallel": true, "self": 0.0003251349553465843, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002796109765768051, "count": 1, "is_parallel": true, "self": 0.0002796109765768051 }, "communicator.exchange": { "total": 0.012896180036477745, "count": 1, "is_parallel": true, "self": 0.012896180036477745 }, "steps_from_proto": { "total": 0.000997247057966888, "count": 2, "is_parallel": true, "self": 0.0002167389029636979, "children": { "_process_rank_one_or_two_observation": { "total": 0.00078050815500319, "count": 8, "is_parallel": true, "self": 0.00078050815500319 } } } } } } }, "UnityEnvironment.step": { "total": 2389.30539528816, "count": 344356, "is_parallel": true, "self": 105.24268618470524, "children": { "UnityEnvironment._generate_step_input": { "total": 73.29048731795046, "count": 344356, "is_parallel": true, "self": 73.29048731795046 }, "communicator.exchange": { "total": 1896.7310156814056, "count": 344356, "is_parallel": true, "self": 1896.7310156814056 }, "steps_from_proto": { "total": 314.0412061040988, "count": 688712, "is_parallel": true, "self": 64.98019582079723, "children": { "_process_rank_one_or_two_observation": { "total": 249.06101028330158, "count": 2754848, "is_parallel": true, "self": 249.06101028330158 } } } } }, "steps_from_proto": { "total": 0.023633707431145012, "count": 48, "is_parallel": true, "self": 0.0049891985254362226, "children": { "_process_rank_one_or_two_observation": { "total": 0.01864450890570879, "count": 192, "is_parallel": true, "self": 0.01864450890570879 } } } } } } } } }, "trainer_advance": { "total": 1245.5812810827047, "count": 344357, "self": 36.74030586180743, "children": { "process_trajectory": { "total": 552.077100536786, "count": 344357, "self": 551.1071592046646, "children": { "RLTrainer._checkpoint": { "total": 0.9699413321213797, "count": 10, "self": 0.9699413321213797 } } }, "_update_policy": { "total": 656.7638746841112, "count": 241, "self": 360.24006106797606, "children": { "TorchPOCAOptimizer.update": { "total": 296.52381361613516, "count": 7230, "self": 296.52381361613516 } } } } } } }, "trainer_threads": { "total": 5.100155249238014e-07, "count": 1, "self": 5.100155249238014e-07 }, "TrainerController._save_models": { "total": 0.09505348990205675, "count": 1, "self": 0.000944610801525414, "children": { "RLTrainer._checkpoint": { "total": 0.09410887910053134, "count": 1, "self": 0.09410887910053134 } } } } } } }