| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 3.22896146774292, | |
| "min": 3.1848373413085938, | |
| "max": 3.2397873401641846, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 46910.3515625, | |
| "min": 17658.828125, | |
| "max": 102906.75, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 878.8333333333334, | |
| "min": 580.0, | |
| "max": 999.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 21092.0, | |
| "min": 9680.0, | |
| "max": 28356.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1207.9839607543527, | |
| "min": 1203.361182298351, | |
| "max": 1209.4159941625653, | |
| "count": 37 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 2415.9679215087053, | |
| "min": 2406.722364596702, | |
| "max": 9656.165338551153, | |
| "count": 37 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 1499626.0, | |
| "min": 1009782.0, | |
| "max": 1499626.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 1499626.0, | |
| "min": 1009782.0, | |
| "max": 1499626.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.0005232731928117573, | |
| "min": -0.004119817167520523, | |
| "max": 0.0015827578026801348, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -0.006279278080910444, | |
| "min": -0.0516546294093132, | |
| "max": 0.016616934910416603, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 2.5139981516986154e-05, | |
| "min": -0.0048939441330730915, | |
| "max": 0.001756390556693077, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 0.00030167977092787623, | |
| "min": -0.05872733145952225, | |
| "max": 0.01756390556693077, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.16666666666666666, | |
| "min": -0.4, | |
| "max": 0.1904666709403197, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -2.0, | |
| "min": -4.0, | |
| "max": 2.2856000512838364, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.16666666666666666, | |
| "min": -0.4, | |
| "max": 0.1904666709403197, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -2.0, | |
| "min": -4.0, | |
| "max": 2.2856000512838364, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 50 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.016666618620123093, | |
| "min": 0.013956846692599357, | |
| "max": 0.022629022784531116, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.016666618620123093, | |
| "min": 0.013956846692599357, | |
| "max": 0.022629022784531116, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0004101419082265541, | |
| "min": 6.887182792070234e-07, | |
| "max": 0.001591083847392255, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0004101419082265541, | |
| "min": 6.887182792070234e-07, | |
| "max": 0.001591083847392255, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.0004095457172904086, | |
| "min": 6.219582786570754e-07, | |
| "max": 0.0015867490273637648, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.0004095457172904086, | |
| "min": 6.219582786570754e-07, | |
| "max": 0.0015867490273637648, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0006, | |
| "min": 0.0006, | |
| "max": 0.0006, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0006, | |
| "min": 0.0006, | |
| "max": 0.0006, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 23 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 23 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1690836134", | |
| "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu", | |
| "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": "1690838130" | |
| }, | |
| "total": 1996.5656753400008, | |
| "count": 1, | |
| "self": 0.5412798930010467, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.060030644000107714, | |
| "count": 1, | |
| "self": 0.060030644000107714 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1995.9643648029996, | |
| "count": 1, | |
| "self": 1.315962397002295, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.08804731500004, | |
| "count": 4, | |
| "self": 2.08804731500004 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1992.333410817998, | |
| "count": 32576, | |
| "self": 1.3532669141413862, | |
| "children": { | |
| "env_step": { | |
| "total": 1143.4442700788622, | |
| "count": 32576, | |
| "self": 962.7638915999123, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 179.8672459990703, | |
| "count": 32576, | |
| "self": 7.80844156814328, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 172.058804430927, | |
| "count": 64698, | |
| "self": 172.058804430927 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.8131324798796413, | |
| "count": 32576, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1980.834241586098, | |
| "count": 32576, | |
| "is_parallel": true, | |
| "self": 1182.166430001218, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.005761311000242131, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0013010019993089372, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.004460309000933194, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.004460309000933194 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.08242809900002612, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0013541799980885116, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0010495550004634424, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0010495550004634424 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.0756327950002742, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0756327950002742 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.004391569001199969, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.000847820002491062, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0035437489987089066, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0035437489987089066 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.009897961000206124, | |
| "count": 6, | |
| "is_parallel": true, | |
| "self": 0.0017937970005732495, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.008104163999632874, | |
| "count": 24, | |
| "is_parallel": true, | |
| "self": 0.008104163999632874 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 798.6579136238797, | |
| "count": 32575, | |
| "is_parallel": true, | |
| "self": 47.85686024690767, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 24.062977560040963, | |
| "count": 32575, | |
| "is_parallel": true, | |
| "self": 24.062977560040963 | |
| }, | |
| "communicator.exchange": { | |
| "total": 570.5423945099328, | |
| "count": 32575, | |
| "is_parallel": true, | |
| "self": 570.5423945099328 | |
| }, | |
| "steps_from_proto": { | |
| "total": 156.19568130699827, | |
| "count": 65150, | |
| "is_parallel": true, | |
| "self": 26.6652478429005, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 129.53043346409777, | |
| "count": 260600, | |
| "is_parallel": true, | |
| "self": 129.53043346409777 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 847.5358738249943, | |
| "count": 32576, | |
| "self": 11.022426634062867, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 125.11756927492934, | |
| "count": 32576, | |
| "self": 124.59364989992991, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.5239193749994229, | |
| "count": 1, | |
| "self": 0.5239193749994229 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 711.3958779160021, | |
| "count": 23, | |
| "self": 131.06789364600354, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 580.3279842699985, | |
| "count": 699, | |
| "self": 580.3279842699985 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.0889998520724475e-06, | |
| "count": 1, | |
| "self": 1.0889998520724475e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.22694318399953772, | |
| "count": 1, | |
| "self": 0.0023119159995985683, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.22463126799993915, | |
| "count": 1, | |
| "self": 0.22463126799993915 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |