{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1654348373413086, "min": 3.143012523651123, "max": 3.1917285919189453, "count": 47 }, "SoccerTwos.Policy.Entropy.sum": { "value": 69994.09375, "min": 12469.833984375, "max": 101995.203125, "count": 47 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 887.3333333333334, "min": 457.125, "max": 999.0, "count": 47 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21296.0, "min": 7992.0, "max": 31968.0, "count": 47 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1209.033305119525, "min": 1205.8941510006202, "max": 1209.660612221576, "count": 31 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4836.1332204781, "min": 2411.7883020012405, "max": 7257.9636733294565, "count": 31 }, "SoccerTwos.Step.mean": { "value": 4999800.0, "min": 4539652.0, "max": 4999800.0, "count": 47 }, "SoccerTwos.Step.sum": { "value": 4999800.0, "min": 4539652.0, "max": 4999800.0, "count": 47 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.006127266213297844, "min": -0.01750943809747696, "max": 0.004200804512947798, "count": 47 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.07352719455957413, "min": -0.22762270271778107, "max": 0.04200804606080055, "count": 47 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.005806541070342064, "min": -0.017375219613313675, "max": 0.0042443894781172276, "count": 47 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.06967849284410477, "min": -0.22587786614894867, "max": 0.0424438938498497, "count": 47 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 47 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 47 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11169999837875366, "min": -0.4166666666666667, "max": 0.2304285764694214, "count": 47 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.340399980545044, "min": -5.0, "max": 3.2260000705718994, "count": 47 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11169999837875366, "min": -0.4166666666666667, "max": 0.2304285764694214, "count": 47 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.340399980545044, "min": -5.0, "max": 3.2260000705718994, "count": 47 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 47 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 47 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014754182616403948, "min": 0.010258695079634587, "max": 0.023413337239374717, "count": 20 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014754182616403948, "min": 0.010258695079634587, "max": 0.023413337239374717, "count": 20 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0016654776758514346, "min": 5.434628244908406e-07, "max": 0.003290623868815601, "count": 20 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0016654776758514346, "min": 5.434628244908406e-07, "max": 0.003290623868815601, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.001665588014293462, "min": 5.792501596602051e-07, "max": 0.0033041236456483603, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.001665588014293462, "min": 5.792501596602051e-07, "max": 0.0033041236456483603, "count": 20 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 20 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 20 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 20 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 20 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 20 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690767013", "python_version": "3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:08:06) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=/content/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics --resume", "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": "1690768169" }, "total": 1155.8800393410002, "count": 1, "self": 0.850588596000307, "children": { "run_training.setup": { "total": 0.020737078000820475, "count": 1, "self": 0.020737078000820475 }, "TrainerController.start_learning": { "total": 1155.008713666999, "count": 1, "self": 0.8899918940569478, "children": { "TrainerController._reset_env": { "total": 4.24025274899941, "count": 4, "self": 4.24025274899941 }, "TrainerController.advance": { "total": 1149.478719135941, "count": 30839, "self": 0.909951285319039, "children": { "env_step": { "total": 940.7512788088661, "count": 30839, "self": 746.9692555987604, "children": { "SubprocessEnvManager._take_step": { "total": 193.28846059587522, "count": 30839, "self": 5.498512304882752, "children": { "TorchPolicy.evaluate": { "total": 187.78994829099247, "count": 61274, "self": 187.78994829099247 } } }, "workers": { "total": 0.49356261423054093, "count": 30839, "self": 0.0, "children": { "worker_root": { "total": 1151.5397765659345, "count": 30839, "is_parallel": true, "self": 520.3601140870705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027938249986618757, "count": 2, "is_parallel": true, "self": 0.0007248569945659256, "children": { "_process_rank_one_or_two_observation": { "total": 0.00206896800409595, "count": 8, "is_parallel": true, "self": 0.00206896800409595 } } }, "UnityEnvironment.step": { "total": 0.039516434000688605, "count": 1, "is_parallel": true, "self": 0.001153601000623894, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008682339994265931, "count": 1, "is_parallel": true, "self": 0.0008682339994265931 }, "communicator.exchange": { "total": 0.03387377500075672, "count": 1, "is_parallel": true, "self": 0.03387377500075672 }, "steps_from_proto": { "total": 0.003620823999881395, "count": 2, "is_parallel": true, "self": 0.0006836849988758331, "children": { "_process_rank_one_or_two_observation": { "total": 0.002937139001005562, "count": 8, "is_parallel": true, "self": 0.002937139001005562 } } } } } } }, "steps_from_proto": { "total": 0.006089714997870033, "count": 6, "is_parallel": true, "self": 0.0011341709996486316, "children": { "_process_rank_one_or_two_observation": { "total": 0.004955543998221401, "count": 24, "is_parallel": true, "self": 0.004955543998221401 } } }, "UnityEnvironment.step": { "total": 631.1735727638661, "count": 30838, "is_parallel": true, "self": 35.18660499447469, "children": { "UnityEnvironment._generate_step_input": { "total": 22.12658273210218, "count": 30838, "is_parallel": true, "self": 22.12658273210218 }, "communicator.exchange": { "total": 457.5699802731524, "count": 30838, "is_parallel": true, "self": 457.5699802731524 }, "steps_from_proto": { "total": 116.29040476413684, "count": 61676, "is_parallel": true, "self": 19.048101971266078, "children": { "_process_rank_one_or_two_observation": { "total": 97.24230279287076, "count": 246704, "is_parallel": true, "self": 97.24230279287076 } } } } } } } } } } }, "trainer_advance": { "total": 207.81748904175583, "count": 30839, "self": 7.11007162349415, "children": { "process_trajectory": { "total": 51.426410633261185, "count": 30839, "self": 51.00422205026189, "children": { "RLTrainer._checkpoint": { "total": 0.42218858299929707, "count": 1, "self": 0.42218858299929707 } } }, "_update_policy": { "total": 149.2810067850005, "count": 20, "self": 97.41269202499825, "children": { "TorchPOCAOptimizer.update": { "total": 51.86831476000225, "count": 627, "self": 51.86831476000225 } } } } } } }, "trainer_threads": { "total": 1.5290006558643654e-06, "count": 1, "self": 1.5290006558643654e-06 }, "TrainerController._save_models": { "total": 0.39974835900102335, "count": 1, "self": 0.01136390900137485, "children": { "RLTrainer._checkpoint": { "total": 0.3883844499996485, "count": 1, "self": 0.3883844499996485 } } } } } } }