{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6355295181274414, "min": 1.5556219816207886, "max": 3.2957351207733154, "count": 2361 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33862.00390625, "min": 7146.287109375, "max": 140531.1875, "count": 2361 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 81.19672131147541, "min": 42.86842105263158, "max": 999.0, "count": 2361 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19812.0, "min": 16132.0, "max": 24572.0, "count": 2361 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1758.5471738754113, "min": 1181.7664894650243, "max": 1767.1975147088438, "count": 2052 }, "SoccerTwos.Self-play.ELO.sum": { "value": 214542.75521280017, "min": 2363.5329789300486, "max": 382132.1488553595, "count": 2052 }, "SoccerTwos.Step.mean": { "value": 23609958.0, "min": 9926.0, "max": 23609958.0, "count": 2361 }, "SoccerTwos.Step.sum": { "value": 23609958.0, "min": 9926.0, "max": 23609958.0, "count": 2361 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.020006421953439713, "min": -0.14947007596492767, "max": 0.1763027161359787, "count": 2361 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.4207770824432373, "min": -19.73004913330078, "max": 22.375396728515625, "count": 2361 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.017882896587252617, "min": -0.14992459118366241, "max": 0.17050811648368835, "count": 2361 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.163830518722534, "min": -19.79004669189453, "max": 22.83205795288086, "count": 2361 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2361 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2361 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.21870743932802816, "min": -0.6153846153846154, "max": 0.4306128957579213, "count": 2361 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -26.463600158691406, "min": -53.23839998245239, "max": 51.03640007972717, "count": 2361 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.21870743932802816, "min": -0.6153846153846154, "max": 0.4306128957579213, "count": 2361 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -26.463600158691406, "min": -53.23839998245239, "max": 51.03640007972717, "count": 2361 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2361 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2361 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012864018611920377, "min": 0.010373547007717813, "max": 0.02504761435945208, "count": 1133 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012864018611920377, "min": 0.010373547007717813, "max": 0.02504761435945208, "count": 1133 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07513934175173441, "min": 1.1720094613328532e-08, "max": 0.11449259718259176, "count": 1133 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07513934175173441, "min": 1.1720094613328532e-08, "max": 0.11449259718259176, "count": 1133 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07576408162713051, "min": 1.091971443637855e-08, "max": 0.11608768875400226, "count": 1133 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07576408162713051, "min": 1.091971443637855e-08, "max": 0.11608768875400226, "count": 1133 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1133 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1133 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1133 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1133 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1133 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1133 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676489818", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/kanagnostopoulos/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1676536863" }, "total": 47044.635964912944, "count": 1, "self": 0.047840380924753845, "children": { "run_training.setup": { "total": 0.006117878016084433, "count": 1, "self": 0.006117878016084433 }, "TrainerController.start_learning": { "total": 47044.582006654, "count": 1, "self": 18.642957511125132, "children": { "TrainerController._reset_env": { "total": 5.02615031064488, "count": 118, "self": 5.02615031064488 }, "TrainerController.advance": { "total": 47020.74202188128, "count": 1600277, "self": 17.32730733056087, "children": { "env_step": { "total": 24164.484697807813, "count": 1600277, "self": 20210.842440662207, "children": { "SubprocessEnvManager._take_step": { "total": 3941.82639939792, "count": 1600277, "self": 113.06567042251118, "children": { "TorchPolicy.evaluate": { "total": 3828.7607289754087, "count": 2987428, "self": 3828.7607289754087 } } }, "workers": { "total": 11.815857747686096, "count": 1600276, "self": 0.0, "children": { "worker_root": { "total": 47006.155200002715, "count": 1600276, "is_parallel": true, "self": 29356.246245485963, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00309389503672719, "count": 2, "is_parallel": true, "self": 0.0006876072147861123, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024062878219410777, "count": 8, "is_parallel": true, "self": 0.0024062878219410777 } } }, "UnityEnvironment.step": { "total": 0.027036591083742678, "count": 1, "is_parallel": true, "self": 0.0009972882689908147, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006459549767896533, "count": 1, "is_parallel": true, "self": 0.0006459549767896533 }, "communicator.exchange": { "total": 0.02278045692946762, "count": 1, "is_parallel": true, "self": 0.02278045692946762 }, "steps_from_proto": { "total": 0.0026128909084945917, "count": 2, "is_parallel": true, "self": 0.00041551387403160334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021973770344629884, "count": 8, "is_parallel": true, "self": 0.0021973770344629884 } } } } } } }, "UnityEnvironment.step": { "total": 17649.61632656539, "count": 1600275, "is_parallel": true, "self": 1373.5061208287952, "children": { "UnityEnvironment._generate_step_input": { "total": 813.9095191607485, "count": 1600275, "is_parallel": true, "self": 813.9095191607485 }, "communicator.exchange": { "total": 11827.893508464564, "count": 1600275, "is_parallel": true, "self": 11827.893508464564 }, "steps_from_proto": { "total": 3634.3071781112812, "count": 3200550, "is_parallel": true, "self": 542.560461330344, "children": { "_process_rank_one_or_two_observation": { "total": 3091.7467167809373, "count": 12802200, "is_parallel": true, "self": 3091.7467167809373 } } } } }, "steps_from_proto": { "total": 0.2926279513631016, "count": 234, "is_parallel": true, "self": 0.04409375973045826, "children": { "_process_rank_one_or_two_observation": { "total": 0.24853419163264334, "count": 936, "is_parallel": true, "self": 0.24853419163264334 } } } } } } } } }, "trainer_advance": { "total": 22838.930016742903, "count": 1600276, "self": 155.09069213434123, "children": { "process_trajectory": { "total": 3293.237239936134, "count": 1600276, "self": 3285.365893873037, "children": { "RLTrainer._checkpoint": { "total": 7.871346063097008, "count": 47, "self": 7.871346063097008 } } }, "_update_policy": { "total": 19390.602084672428, "count": 1133, "self": 2635.546203625505, "children": { "TorchPOCAOptimizer.update": { "total": 16755.055881046923, "count": 33990, "self": 16755.055881046923 } } } } } } }, "trainer_threads": { "total": 5.899928510189056e-07, "count": 1, "self": 5.899928510189056e-07 }, "TrainerController._save_models": { "total": 0.17087636096403003, "count": 1, "self": 0.0013726209290325642, "children": { "RLTrainer._checkpoint": { "total": 0.16950374003499746, "count": 1, "self": 0.16950374003499746 } } } } } } }