| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.6226943731307983, | |
| "min": 1.5611810684204102, | |
| "max": 1.6945871114730835, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 32038.478515625, | |
| "min": 14358.2451171875, | |
| "max": 36540.3515625, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 52.46236559139785, | |
| "min": 43.67857142857143, | |
| "max": 84.9298245614035, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19516.0, | |
| "min": 6196.0, | |
| "max": 20504.0, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1762.0327533333198, | |
| "min": 1716.434584527975, | |
| "max": 1774.3924545996833, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 327738.0921199975, | |
| "min": 73048.80667321243, | |
| "max": 393653.9862547412, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 5719937.0, | |
| "min": 5049921.0, | |
| "max": 5719937.0, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 5719937.0, | |
| "min": 5049921.0, | |
| "max": 5719937.0, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.011084538884460926, | |
| "min": -0.11968474090099335, | |
| "max": 0.09241729974746704, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -2.0617241859436035, | |
| "min": -20.514877319335938, | |
| "max": 13.677760124206543, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.008946689777076244, | |
| "min": -0.12291066348552704, | |
| "max": 0.099024698138237, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -1.6640843152999878, | |
| "min": -20.696678161621094, | |
| "max": 14.655655860900879, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.1161763443741747, | |
| "min": -0.27891227968952115, | |
| "max": 0.23409999866743345, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -21.608800053596497, | |
| "min": -47.109400033950806, | |
| "max": 36.34579974412918, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.1161763443741747, | |
| "min": -0.27891227968952115, | |
| "max": 0.23409999866743345, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -21.608800053596497, | |
| "min": -47.109400033950806, | |
| "max": 36.34579974412918, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 68 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.014650713512673974, | |
| "min": 0.013964531397505198, | |
| "max": 0.0222065897192806, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.014650713512673974, | |
| "min": 0.013964531397505198, | |
| "max": 0.0222065897192806, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.14041342288255693, | |
| "min": 0.10347647716601689, | |
| "max": 0.15248785316944122, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.14041342288255693, | |
| "min": 0.10347647716601689, | |
| "max": 0.15248785316944122, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.14387492487827938, | |
| "min": 0.10560697962840399, | |
| "max": 0.1569852575659752, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.14387492487827938, | |
| "min": 0.10560697962840399, | |
| "max": 0.1569852575659752, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0005000000000000001, | |
| "min": 0.0005000000000000001, | |
| "max": 0.0005000000000000001, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0005000000000000001, | |
| "min": 0.0005000000000000001, | |
| "max": 0.0005000000000000001, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 32 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 32 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1711938319", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/home/diego/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=Soccer-first_try --resume", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.2.2+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1711939540" | |
| }, | |
| "total": 1220.6646349760003, | |
| "count": 1, | |
| "self": 0.004954990000442194, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.02140686100028688, | |
| "count": 1, | |
| "self": 0.02140686100028688 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1220.6382731249996, | |
| "count": 1, | |
| "self": 0.9138819871932355, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.6859687379992465, | |
| "count": 4, | |
| "self": 4.6859687379992465 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1214.5627193438077, | |
| "count": 47052, | |
| "self": 0.9671358051036805, | |
| "children": { | |
| "env_step": { | |
| "total": 868.0697374158935, | |
| "count": 47052, | |
| "self": 658.5315288138754, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 208.9358467241982, | |
| "count": 47052, | |
| "self": 5.634811928912313, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 203.3010347952859, | |
| "count": 85158, | |
| "self": 203.3010347952859 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.6023618778199307, | |
| "count": 47051, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1218.885470208821, | |
| "count": 47051, | |
| "is_parallel": true, | |
| "self": 667.6634703658092, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.00190659300005791, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00044139500005258014, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.00146519800000533, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.00146519800000533 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.031175416000223777, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000873470999977144, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00036761999945156276, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00036761999945156276 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.026747050000267336, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.026747050000267336 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.003187275000527734, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0004993780021322891, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.002687896998395445, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.002687896998395445 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.006322206000731967, | |
| "count": 6, | |
| "is_parallel": true, | |
| "self": 0.0011802860035459162, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.005141919997186051, | |
| "count": 24, | |
| "is_parallel": true, | |
| "self": 0.005141919997186051 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 551.2156776370111, | |
| "count": 47050, | |
| "is_parallel": true, | |
| "self": 30.82661347364592, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 17.47474026310556, | |
| "count": 47050, | |
| "is_parallel": true, | |
| "self": 17.47474026310556 | |
| }, | |
| "communicator.exchange": { | |
| "total": 418.99085925802683, | |
| "count": 47050, | |
| "is_parallel": true, | |
| "self": 418.99085925802683 | |
| }, | |
| "steps_from_proto": { | |
| "total": 83.92346464223283, | |
| "count": 94100, | |
| "is_parallel": true, | |
| "self": 15.252674924946405, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 68.67078971728643, | |
| "count": 376400, | |
| "is_parallel": true, | |
| "self": 68.67078971728643 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 345.52584612281044, | |
| "count": 47051, | |
| "self": 5.916683962825118, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 120.71215693498834, | |
| "count": 47051, | |
| "self": 120.25618933298847, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.4559676019998733, | |
| "count": 1, | |
| "self": 0.4559676019998733 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 218.89700522499697, | |
| "count": 33, | |
| "self": 77.10713810897596, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 141.78986711602101, | |
| "count": 990, | |
| "self": 141.78986711602101 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.3629996828967705e-06, | |
| "count": 1, | |
| "self": 1.3629996828967705e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.4757016929997917, | |
| "count": 1, | |
| "self": 0.009613814998374437, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.46608787800141727, | |
| "count": 1, | |
| "self": 0.46608787800141727 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |