{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.3941988945007324, "min": 2.3131208419799805, "max": 2.7397079467773438, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 51484.8515625, "min": 43049.46875, "max": 61992.546875, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.87640449438202, "min": 44.518181818181816, "max": 82.40350877192982, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19892.0, "min": 18704.0, "max": 20792.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1447.8529248817329, "min": 1362.6837262167921, "max": 1452.3680940759016, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 257717.82062894845, "min": 156982.38206840446, "max": 316908.9906318673, "count": 100 }, "SoccerTwos.Step.mean": { "value": 4999788.0, "min": 4009916.0, "max": 4999788.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 4999788.0, "min": 4009916.0, "max": 4999788.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003941728733479977, "min": -0.07890141010284424, "max": 0.12007641047239304, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.7016277313232422, "min": -10.651690483093262, "max": 20.533065795898438, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006369381677359343, "min": -0.074931800365448, "max": 0.11935584992170334, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.1337499618530273, "min": -10.115793228149414, "max": 20.132320404052734, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.027782022283318338, "min": -0.22990908989539513, "max": 0.3713333321114381, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 4.945199966430664, "min": -35.852399826049805, "max": 53.47199982404709, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.027782022283318338, "min": -0.22990908989539513, "max": 0.3713333321114381, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 4.945199966430664, "min": -35.852399826049805, "max": 53.47199982404709, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018181406586275747, "min": 0.011711180448764935, "max": 0.024391871690750123, "count": 48 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018181406586275747, "min": 0.011711180448764935, "max": 0.024391871690750123, "count": 48 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08860972747206688, "min": 0.06452058975895246, "max": 0.09899336422483127, "count": 48 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08860972747206688, "min": 0.06452058975895246, "max": 0.09899336422483127, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09137522255380949, "min": 0.06540971485277017, "max": 0.10181420395771662, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09137522255380949, "min": 0.06540971485277017, "max": 0.10181420395771662, "count": 48 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 48 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 48 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 48 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 48 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 48 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 48 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677186599", "python_version": "3.8.15 | packaged by conda-forge | (default, Nov 22 2022, 08:49:35) \n[GCC 10.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --resume --initialize-from=SoccerTwos --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1677208215" }, "total": 21616.813935551, "count": 1, "self": 0.7073853080000845, "children": { "run_training.setup": { "total": 0.016974316000016643, "count": 1, "self": 0.016974316000016643 }, "TrainerController.start_learning": { "total": 21616.089575927, "count": 1, "self": 3.220351229869266, "children": { "TrainerController._reset_env": { "total": 1.9565833170044584, "count": 6, "self": 1.9565833170044584 }, "TrainerController.advance": { "total": 21610.641849352127, "count": 69432, "self": 3.5971864697057754, "children": { "env_step": { "total": 14589.285470454291, "count": 69432, "self": 14164.850334149665, "children": { "SubprocessEnvManager._take_step": { "total": 422.3507650345132, "count": 69432, "self": 15.411872300947664, "children": { "TorchPolicy.evaluate": { "total": 406.9388927335655, "count": 125404, "self": 406.9388927335655 } } }, "workers": { "total": 2.0843712701137633, "count": 69432, "self": 0.0, "children": { "worker_root": { "total": 21579.579130355, "count": 69432, "is_parallel": true, "self": 7797.377723194233, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005202019000023483, "count": 2, "is_parallel": true, "self": 0.0010196599999972022, "children": { "_process_rank_one_or_two_observation": { "total": 0.004182359000026281, "count": 8, "is_parallel": true, "self": 0.004182359000026281 } } }, "UnityEnvironment.step": { "total": 0.3199886740000011, "count": 1, "is_parallel": true, "self": 0.0028174480000302538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.003394438999976046, "count": 1, "is_parallel": true, "self": 0.003394438999976046 }, "communicator.exchange": { "total": 0.304528227999981, "count": 1, "is_parallel": true, "self": 0.304528227999981 }, "steps_from_proto": { "total": 0.009248559000013756, "count": 2, "is_parallel": true, "self": 0.0008982999999602725, "children": { "_process_rank_one_or_two_observation": { "total": 0.008350259000053484, "count": 8, "is_parallel": true, "self": 0.008350259000053484 } } } } } } }, "steps_from_proto": { "total": 0.01767323799941778, "count": 10, "is_parallel": true, "self": 0.0031686419932270837, "children": { "_process_rank_one_or_two_observation": { "total": 0.014504596006190695, "count": 40, "is_parallel": true, "self": 0.014504596006190695 } } }, "UnityEnvironment.step": { "total": 13782.183733922768, "count": 69431, "is_parallel": true, "self": 68.27179831056492, "children": { "UnityEnvironment._generate_step_input": { "total": 297.5665126266925, "count": 69431, "is_parallel": true, "self": 297.5665126266925 }, "communicator.exchange": { "total": 12950.69541392179, "count": 69431, "is_parallel": true, "self": 12950.69541392179 }, "steps_from_proto": { "total": 465.65000906371944, "count": 138862, "is_parallel": true, "self": 81.39833913502974, "children": { "_process_rank_one_or_two_observation": { "total": 384.2516699286897, "count": 555448, "is_parallel": true, "self": 384.2516699286897 } } } } } } } } } } }, "trainer_advance": { "total": 7017.759192428131, "count": 69432, "self": 23.725909247148593, "children": { "process_trajectory": { "total": 952.3833110709934, "count": 69432, "self": 951.8914804129913, "children": { "RLTrainer._checkpoint": { "total": 0.4918306580020726, "count": 2, "self": 0.4918306580020726 } } }, "_update_policy": { "total": 6041.64997210999, "count": 48, "self": 204.19424143499418, "children": { "TorchPOCAOptimizer.update": { "total": 5837.455730674996, "count": 1440, "self": 5837.455730674996 } } } } } } }, "trainer_threads": { "total": 8.499991963617504e-07, "count": 1, "self": 8.499991963617504e-07 }, "TrainerController._save_models": { "total": 0.270791177998035, "count": 1, "self": 0.004163938996498473, "children": { "RLTrainer._checkpoint": { "total": 0.2666272390015365, "count": 1, "self": 0.2666272390015365 } } } } } } }