{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.4417953491210938, "min": 2.4372684955596924, "max": 3.2034013271331787, "count": 351 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48992.1796875, "min": 18580.30078125, "max": 114449.1015625, "count": 351 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 44.027027027027025, "min": 43.07964601769911, "max": 999.0, "count": 351 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19548.0, "min": 3996.0, "max": 32868.0, "count": 351 }, "SoccerTwos.Step.mean": { "value": 6089986.0, "min": 2529737.0, "max": 6089986.0, "count": 357 }, "SoccerTwos.Step.sum": { "value": 6089986.0, "min": 2529737.0, "max": 6089986.0, "count": 357 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.047659702599048615, "min": -0.06996490806341171, "max": 0.17576617002487183, "count": 357 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 10.580453872680664, "min": -8.325823783874512, "max": 26.9212646484375, "count": 357 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04913307726383209, "min": -0.07348953932523727, "max": 0.18069696426391602, "count": 357 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 10.907543182373047, "min": -8.745255470275879, "max": 26.480384826660156, "count": 357 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 357 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 357 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.08971351250871881, "min": -0.6561125009320676, "max": 0.49619725958941735, "count": 357 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 19.916399776935577, "min": -37.92640018463135, "max": 62.96359956264496, "count": 357 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.08971351250871881, "min": -0.6561125009320676, "max": 0.49619725958941735, "count": 357 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 19.916399776935577, "min": -37.92640018463135, "max": 62.96359956264496, "count": 357 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 357 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 357 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013407751137856394, "min": 0.01142314199047784, "max": 0.02425788139613966, "count": 164 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013407751137856394, "min": 0.01142314199047784, "max": 0.02425788139613966, "count": 164 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09530262673894564, "min": 6.020134222239903e-08, "max": 0.10161784266432126, "count": 164 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09530262673894564, "min": 6.020134222239903e-08, "max": 0.10161784266432126, "count": 164 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09778229296207427, "min": 1.1880357154344287e-07, "max": 0.10410436963041624, "count": 164 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09778229296207427, "min": 1.1880357154344287e-07, "max": 0.10410436963041624, "count": 164 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 164 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 164 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 164 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 164 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 164 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 164 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1393.6875639312832, "min": 1175.020763080963, "max": 1407.4624380333469, "count": 257 }, "SoccerTwos.Self-play.ELO.sum": { "value": 309398.63919274486, "min": 2350.041526161926, "max": 312828.9320947636, "count": 257 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726853619", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/loboronan/miniconda3/envs/unityrl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726862084" }, "total": 8003.731036661001, "count": 1, "self": 0.1642863410015707, "children": { "run_training.setup": { "total": 0.01574568600000248, "count": 1, "self": 0.01574568600000248 }, "TrainerController.start_learning": { "total": 8003.551004634, "count": 1, "self": 5.11542567806282, "children": { "TrainerController._reset_env": { "total": 3.500413088002176, "count": 19, "self": 3.500413088002176 }, "TrainerController.advance": { "total": 7994.509755703934, "count": 235191, "self": 5.586768086869597, "children": { "env_step": { "total": 6542.052595024812, "count": 235191, "self": 4133.565731688963, "children": { "SubprocessEnvManager._take_step": { "total": 2405.351513774882, "count": 235191, "self": 30.02797726479821, "children": { "TorchPolicy.evaluate": { "total": 2375.3235365100836, "count": 455834, "self": 2375.3235365100836 } } }, "workers": { "total": 3.1353495609669153, "count": 235190, "self": 0.0, "children": { "worker_root": { "total": 7991.384502473039, "count": 235190, "is_parallel": true, "self": 4415.152569256068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029765129999930195, "count": 2, "is_parallel": true, "self": 0.0010946439999770519, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018818690000159677, "count": 8, "is_parallel": true, "self": 0.0018818690000159677 } } }, "UnityEnvironment.step": { "total": 0.02766064100001131, "count": 1, "is_parallel": true, "self": 0.0006161299999973835, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035528300000464696, "count": 1, "is_parallel": true, "self": 0.00035528300000464696 }, "communicator.exchange": { "total": 0.02512660099998243, "count": 1, "is_parallel": true, "self": 0.02512660099998243 }, "steps_from_proto": { "total": 0.0015626270000268505, "count": 2, "is_parallel": true, "self": 0.00036540899998271925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011972180000441313, "count": 8, "is_parallel": true, "self": 0.0011972180000441313 } } } } } } }, "steps_from_proto": { "total": 0.024961540998958753, "count": 36, "is_parallel": true, "self": 0.005609905998994691, "children": { "_process_rank_one_or_two_observation": { "total": 0.019351634999964062, "count": 144, "is_parallel": true, "self": 0.019351634999964062 } } }, "UnityEnvironment.step": { "total": 3576.2069716759725, "count": 235189, "is_parallel": true, "self": 99.84989229992061, "children": { "UnityEnvironment._generate_step_input": { "total": 72.77683382908867, "count": 235189, "is_parallel": true, "self": 72.77683382908867 }, "communicator.exchange": { "total": 3064.8591148571395, "count": 235189, "is_parallel": true, "self": 3064.8591148571395 }, "steps_from_proto": { "total": 338.7211306898232, "count": 470378, "is_parallel": true, "self": 76.59657505344228, "children": { "_process_rank_one_or_two_observation": { "total": 262.12455563638093, "count": 1881512, "is_parallel": true, "self": 262.12455563638093 } } } } } } } } } } }, "trainer_advance": { "total": 1446.8703925922532, "count": 235190, "self": 37.20655809023424, "children": { "process_trajectory": { "total": 668.5377125160178, "count": 235190, "self": 666.3401519490178, "children": { "RLTrainer._checkpoint": { "total": 2.1975605669999823, "count": 7, "self": 2.1975605669999823 } } }, "_update_policy": { "total": 741.1261219860012, "count": 164, "self": 319.34207435801346, "children": { "TorchPOCAOptimizer.update": { "total": 421.7840476279877, "count": 5031, "self": 421.7840476279877 } } } } } } }, "trainer_threads": { "total": 9.180002962239087e-07, "count": 1, "self": 9.180002962239087e-07 }, "TrainerController._save_models": { "total": 0.42540924599961727, "count": 1, "self": 0.013648916999954963, "children": { "RLTrainer._checkpoint": { "total": 0.4117603289996623, "count": 1, "self": 0.4117603289996623 } } } } } } }