| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.6468571424484253, | |
| "min": 1.620234727859497, | |
| "max": 3.2958309650421143, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 34518.125, | |
| "min": 20440.189453125, | |
| "max": 113663.703125, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 129.81578947368422, | |
| "min": 73.53731343283582, | |
| "max": 999.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19732.0, | |
| "min": 3996.0, | |
| "max": 29968.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1283.8520896738241, | |
| "min": 1186.7449991089873, | |
| "max": 1292.4892967539745, | |
| "count": 1623 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 97572.75881521063, | |
| "min": 2373.4899982179745, | |
| "max": 168127.30851741313, | |
| "count": 1623 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 16279960.0, | |
| "min": 9678.0, | |
| "max": 16279960.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 16279960.0, | |
| "min": 9678.0, | |
| "max": 16279960.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.0008682604529894888, | |
| "min": -0.1442578285932541, | |
| "max": 0.15217438340187073, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 0.06598779559135437, | |
| "min": -13.073843002319336, | |
| "max": 15.521787643432617, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.004778760951012373, | |
| "min": -0.1425202637910843, | |
| "max": 0.15821237862110138, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -0.3631858229637146, | |
| "min": -13.25438404083252, | |
| "max": 16.137662887573242, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": 0.05728421242613541, | |
| "min": -0.6153846153846154, | |
| "max": 0.5539310389551623, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 4.3536001443862915, | |
| "min": -49.283599853515625, | |
| "max": 37.99500036239624, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.05728421242613541, | |
| "min": -0.6153846153846154, | |
| "max": 0.5539310389551623, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 4.3536001443862915, | |
| "min": -49.283599853515625, | |
| "max": 37.99500036239624, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1628 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.06345888649711924, | |
| "min": 0.014404559491958934, | |
| "max": 0.06696532642235979, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.06345888649711924, | |
| "min": 0.014404559491958934, | |
| "max": 0.06696532642235979, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0351909302175045, | |
| "min": 0.0010329000597266713, | |
| "max": 0.05442078304477036, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0351909302175045, | |
| "min": 0.0010329000597266713, | |
| "max": 0.05442078304477036, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.03798762366641313, | |
| "min": 0.0010328145443054381, | |
| "max": 0.0717328670900315, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.03798762366641313, | |
| "min": 0.0010328145443054381, | |
| "max": 0.0717328670900315, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003837498200625461, | |
| "min": 0.0003837498200625461, | |
| "max": 0.0003999655760086059, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003837498200625461, | |
| "min": 0.0003837498200625461, | |
| "max": 0.0003999655760086059, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.19593745400000004, | |
| "min": 0.19593745400000004, | |
| "max": 0.19999139400000002, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.19593745400000004, | |
| "min": 0.19593745400000004, | |
| "max": 0.19999139400000002, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.004797278954599999, | |
| "min": 0.004797278954599999, | |
| "max": 0.0049995705606, | |
| "count": 492 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.004797278954599999, | |
| "min": 0.004797278954599999, | |
| "max": 0.0049995705606, | |
| "count": 492 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1692499201", | |
| "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", | |
| "command_line_arguments": "/home/victor/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwosV2 --no-graphics --force", | |
| "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": "1692537155" | |
| }, | |
| "total": 37954.460568632, | |
| "count": 1, | |
| "self": 0.0043710970057873055, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.050531484997918596, | |
| "count": 1, | |
| "self": 0.050531484997918596 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 37954.40566604999, | |
| "count": 1, | |
| "self": 22.15096920770884, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.2845096030177956, | |
| "count": 9, | |
| "self": 3.2845096030177956 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 37928.455804075245, | |
| "count": 1069677, | |
| "self": 20.294769567037292, | |
| "children": { | |
| "env_step": { | |
| "total": 25022.445690085602, | |
| "count": 1069677, | |
| "self": 16364.367602574126, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 8644.768758229864, | |
| "count": 1069677, | |
| "self": 152.85128560423618, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 8491.917472625628, | |
| "count": 2037238, | |
| "self": 8491.917472625628 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 13.309329281612008, | |
| "count": 1069677, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 37890.355768174464, | |
| "count": 1069677, | |
| "is_parallel": true, | |
| "self": 23835.39968843469, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0022201940009836107, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0006396969947672915, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0015804970062163193, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0015804970062163193 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.022530100999574643, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003971999976783991, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0003426000002946239, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003426000002946239 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.020514301002549473, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.020514301002549473 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0012759999990521464, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00028509999901871197, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0009909000000334345, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0009909000000334345 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 14054.945545716775, | |
| "count": 1069676, | |
| "is_parallel": true, | |
| "self": 441.5165943916036, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 323.9747311235078, | |
| "count": 1069676, | |
| "is_parallel": true, | |
| "self": 323.9747311235078 | |
| }, | |
| "communicator.exchange": { | |
| "total": 11894.385197817792, | |
| "count": 1069676, | |
| "is_parallel": true, | |
| "self": 11894.385197817792 | |
| }, | |
| "steps_from_proto": { | |
| "total": 1395.069022383872, | |
| "count": 2139352, | |
| "is_parallel": true, | |
| "self": 296.86871285547386, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1098.200309528398, | |
| "count": 8557408, | |
| "is_parallel": true, | |
| "self": 1098.200309528398 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.01053402300021844, | |
| "count": 16, | |
| "is_parallel": true, | |
| "self": 0.0022184619956533425, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.008315561004565097, | |
| "count": 64, | |
| "is_parallel": true, | |
| "self": 0.008315561004565097 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 12885.715344422606, | |
| "count": 1069677, | |
| "self": 156.89693492608785, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 4022.541019220531, | |
| "count": 1069677, | |
| "self": 4013.206508934527, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 9.334510286003933, | |
| "count": 16, | |
| "self": 9.334510286003933 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 8706.277390275987, | |
| "count": 493, | |
| "self": 3299.628536370419, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 5406.648853905568, | |
| "count": 39440, | |
| "self": 5406.648853905568 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.700012944638729e-06, | |
| "count": 1, | |
| "self": 1.700012944638729e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.514381464003236, | |
| "count": 1, | |
| "self": 0.009308854991104454, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.5050726090121316, | |
| "count": 1, | |
| "self": 0.5050726090121316 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |