| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 2.657888412475586, | |
| "min": 2.657888412475586, | |
| "max": 3.2957236766815186, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 55539.23828125, | |
| "min": 14741.529296875, | |
| "max": 105463.15625, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 75.73846153846154, | |
| "min": 65.14864864864865, | |
| "max": 999.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19692.0, | |
| "min": 4548.0, | |
| "max": 30124.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1386.2681286181073, | |
| "min": 1200.2449734819195, | |
| "max": 1396.1038562938586, | |
| "count": 170 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 180214.85672035394, | |
| "min": 2400.489946963839, | |
| "max": 205106.69011488685, | |
| "count": 170 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 1749992.0, | |
| "min": 9078.0, | |
| "max": 1749992.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 1749992.0, | |
| "min": 9078.0, | |
| "max": 1749992.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.015134832821786404, | |
| "min": -0.03400610014796257, | |
| "max": 0.22032798826694489, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 1.967528223991394, | |
| "min": -2.22676157951355, | |
| "max": 25.89499855041504, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.016398712992668152, | |
| "min": -0.0341365747153759, | |
| "max": 0.22337739169597626, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 2.1318325996398926, | |
| "min": -1.9799213409423828, | |
| "max": 26.016578674316406, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.1394676923751831, | |
| "min": -0.6666666666666666, | |
| "max": 0.4782557370232754, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -18.130800008773804, | |
| "min": -22.25000011920929, | |
| "max": 46.45100021362305, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.1394676923751831, | |
| "min": -0.6666666666666666, | |
| "max": 0.4782557370232754, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -18.130800008773804, | |
| "min": -22.25000011920929, | |
| "max": 46.45100021362305, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 175 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.014425198807536314, | |
| "min": 0.011495149041244683, | |
| "max": 0.022163717014094194, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.014425198807536314, | |
| "min": 0.011495149041244683, | |
| "max": 0.022163717014094194, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.06796828570465246, | |
| "min": 0.0005441805726150051, | |
| "max": 0.07227968672911327, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.06796828570465246, | |
| "min": 0.0005441805726150051, | |
| "max": 0.07227968672911327, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.06986609995365142, | |
| "min": 0.0005505990595944847, | |
| "max": 0.07365259279807408, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.06986609995365142, | |
| "min": 0.0005505990595944847, | |
| "max": 0.07365259279807408, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.19999999999999996, | |
| "max": 0.20000000000000007, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.19999999999999996, | |
| "max": 0.20000000000000007, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 82 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 82 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1675496556", | |
| "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", | |
| "mlagents_version": "0.29.0.dev0", | |
| "mlagents_envs_version": "0.29.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.8.1+cu102", | |
| "numpy_version": "1.21.6", | |
| "end_time_seconds": "1675500123" | |
| }, | |
| "total": 3567.1157116850004, | |
| "count": 1, | |
| "self": 0.38995706100013194, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.12406606999991254, | |
| "count": 1, | |
| "self": 0.12406606999991254 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 3566.6016885540002, | |
| "count": 1, | |
| "self": 2.5552655759602203, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 11.077153099000952, | |
| "count": 7, | |
| "self": 11.077153099000952 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 3552.968809056039, | |
| "count": 114262, | |
| "self": 2.863754190096188, | |
| "children": { | |
| "env_step": { | |
| "total": 2787.9899902270085, | |
| "count": 114262, | |
| "self": 2176.454435612988, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 609.9606745129976, | |
| "count": 114262, | |
| "self": 18.856439643956037, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 591.1042348690415, | |
| "count": 222602, | |
| "self": 117.86353533415661, | |
| "children": { | |
| "TorchPolicy.sample_actions": { | |
| "total": 473.2406995348849, | |
| "count": 222602, | |
| "self": 473.2406995348849 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 1.5748801010225861, | |
| "count": 114261, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 3559.806630536064, | |
| "count": 114261, | |
| "is_parallel": true, | |
| "self": 1714.8426980490776, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.006528958999979295, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0034178479999127376, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0031111110000665576, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0031111110000665576 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.07459809600004519, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0010330710000516774, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0006686719999606794, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006686719999606794 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.05843402600009995, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.05843402600009995 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.014462326999932884, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.008763741999928243, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.005698585000004641, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.005698585000004641 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1844.9486983879863, | |
| "count": 114260, | |
| "is_parallel": true, | |
| "self": 101.10968987900787, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 72.27898529695847, | |
| "count": 114260, | |
| "is_parallel": true, | |
| "self": 72.27898529695847 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1329.5433840110036, | |
| "count": 114260, | |
| "is_parallel": true, | |
| "self": 1329.5433840110036 | |
| }, | |
| "steps_from_proto": { | |
| "total": 342.01663920101623, | |
| "count": 228520, | |
| "is_parallel": true, | |
| "self": 68.58797477892244, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 273.4286644220938, | |
| "count": 914080, | |
| "is_parallel": true, | |
| "self": 273.4286644220938 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.015234099000053902, | |
| "count": 12, | |
| "is_parallel": true, | |
| "self": 0.0030179560010310524, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.01221614299902285, | |
| "count": 48, | |
| "is_parallel": true, | |
| "self": 0.01221614299902285 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 762.1150646389342, | |
| "count": 114261, | |
| "self": 19.26499103793367, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 257.3978115079997, | |
| "count": 114261, | |
| "self": 256.740726689, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.6570848189996923, | |
| "count": 3, | |
| "self": 0.6570848189996923 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 485.45226209300085, | |
| "count": 82, | |
| "self": 297.09873524500824, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 188.3535268479926, | |
| "count": 2472, | |
| "self": 188.3535268479926 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.168999915535096e-06, | |
| "count": 1, | |
| "self": 1.168999915535096e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.0004596540002239635, | |
| "count": 1, | |
| "self": 3.9323000237345695e-05, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.0004203309999866178, | |
| "count": 1, | |
| "self": 0.0004203309999866178 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |