| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.4408972263336182, | |
| "min": 1.34647798538208, | |
| "max": 3.2957446575164795, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 26696.943359375, | |
| "min": 15579.70703125, | |
| "max": 114898.7109375, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 66.20270270270271, | |
| "min": 39.77049180327869, | |
| "max": 999.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19596.0, | |
| "min": 6032.0, | |
| "max": 30900.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1646.8488571288406, | |
| "min": 1188.6659502990287, | |
| "max": 1747.9718014571458, | |
| "count": 4499 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 243733.63085506842, | |
| "min": 2377.3319005980575, | |
| "max": 390871.28502691246, | |
| "count": 4499 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 45159895.0, | |
| "min": 9480.0, | |
| "max": 45159895.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 45159895.0, | |
| "min": 9480.0, | |
| "max": 45159895.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.07225735485553741, | |
| "min": -0.1587270200252533, | |
| "max": 0.1867164969444275, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -10.694087982177734, | |
| "min": -24.761415481567383, | |
| "max": 28.941057205200195, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.07493644207715988, | |
| "min": -0.15862877666950226, | |
| "max": 0.19069910049438477, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -11.090593338012695, | |
| "min": -24.746089935302734, | |
| "max": 29.558361053466797, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.17831621741926348, | |
| "min": -0.6733818198695327, | |
| "max": 0.4627111121120616, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -26.390800178050995, | |
| "min": -73.69519984722137, | |
| "max": 55.13080018758774, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.17831621741926348, | |
| "min": -0.6733818198695327, | |
| "max": 0.4627111121120616, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -26.390800178050995, | |
| "min": -73.69519984722137, | |
| "max": 55.13080018758774, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 4516 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.021313193761549578, | |
| "min": 0.009113810799802499, | |
| "max": 0.02654586935726305, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.021313193761549578, | |
| "min": 0.009113810799802499, | |
| "max": 0.02654586935726305, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0957459956407547, | |
| "min": 4.403265850972578e-05, | |
| "max": 0.12643185531099638, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0957459956407547, | |
| "min": 4.403265850972578e-05, | |
| "max": 0.12643185531099638, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.09621889839569728, | |
| "min": 4.428583324624924e-05, | |
| "max": 0.1395223173002402, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.09621889839569728, | |
| "min": 4.428583324624924e-05, | |
| "max": 0.1395223173002402, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 2187 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 2187 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1701097720", | |
| "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "\\\\?\\C:\\Users\\Aditya\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.1.1+cpu", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1701161699" | |
| }, | |
| "total": 63977.16567700001, | |
| "count": 1, | |
| "self": 0.17009470000630245, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.09332970000104979, | |
| "count": 1, | |
| "self": 0.09332970000104979 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 63976.902252600004, | |
| "count": 1, | |
| "self": 38.01585670054192, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 7.724854799977038, | |
| "count": 226, | |
| "self": 7.724854799977038 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 63931.085107899504, | |
| "count": 3105144, | |
| "self": 36.76736970519414, | |
| "children": { | |
| "env_step": { | |
| "total": 25439.190738883335, | |
| "count": 3105144, | |
| "self": 20010.848189444747, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 5404.875475931738, | |
| "count": 3105144, | |
| "self": 236.41763825167436, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 5168.457837680064, | |
| "count": 5674896, | |
| "self": 5168.457837680064 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 23.467073506850284, | |
| "count": 3105144, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 63917.17435837537, | |
| "count": 3105144, | |
| "is_parallel": true, | |
| "self": 47931.852333021, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.21264499996323138, | |
| "count": 452, | |
| "is_parallel": true, | |
| "self": 0.04078390053473413, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.17186109942849725, | |
| "count": 1808, | |
| "is_parallel": true, | |
| "self": 0.17186109942849725 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 15985.109380354406, | |
| "count": 3105144, | |
| "is_parallel": true, | |
| "self": 843.2959519782453, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 593.3013080957462, | |
| "count": 3105144, | |
| "is_parallel": true, | |
| "self": 593.3013080957462 | |
| }, | |
| "communicator.exchange": { | |
| "total": 11990.734174017853, | |
| "count": 3105144, | |
| "is_parallel": true, | |
| "self": 11990.734174017853 | |
| }, | |
| "steps_from_proto": { | |
| "total": 2557.777946262562, | |
| "count": 6210288, | |
| "is_parallel": true, | |
| "self": 479.7330762423808, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 2078.0448700201814, | |
| "count": 24841152, | |
| "is_parallel": true, | |
| "self": 2078.0448700201814 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 38455.126999310974, | |
| "count": 3105144, | |
| "self": 343.00531288038474, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 7399.575904130703, | |
| "count": 3105144, | |
| "self": 7392.998859030311, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 6.577045100391842, | |
| "count": 90, | |
| "self": 6.577045100391842 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 30712.545782299887, | |
| "count": 2188, | |
| "self": 3519.4821614015964, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 27193.06362089829, | |
| "count": 65621, | |
| "self": 27193.06362089829 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 7.00005330145359e-07, | |
| "count": 1, | |
| "self": 7.00005330145359e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.07643249997636303, | |
| "count": 1, | |
| "self": 0.0034460999886505306, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.0729863999877125, | |
| "count": 1, | |
| "self": 0.0729863999877125 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |