{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7575644254684448, "min": 1.493360996246338, "max": 3.2957265377044678, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40494.28515625, "min": 15558.314453125, "max": 119975.8828125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 483.6666666666667, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 14408.0, "max": 25072.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.3176929592012, "min": 1189.3807875295865, "max": 1198.1055180402539, "count": 61 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2388.6353859184023, "min": 2380.039079295345, "max": 14377.266216483047, "count": 61 }, "SoccerTwos.Step.mean": { "value": 4999778.0, "min": 9554.0, "max": 4999778.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999778.0, "min": 9554.0, "max": 4999778.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 3.301718243164942e-05, "min": -0.06894075125455856, "max": 0.13561339676380157, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.00033017180976457894, "min": -0.6894075274467468, "max": 1.572661280632019, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -6.329694588202983e-05, "min": -0.01316123828291893, "max": 0.1496446281671524, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.0006329694297164679, "min": -0.14477361738681793, "max": 1.572928786277771, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.4676800012588501, "max": 0.15946666399637857, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.0152000188827515, "max": 1.913599967956543, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.4676800012588501, "max": 0.15946666399637857, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.0152000188827515, "max": 1.913599967956543, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017498819755079845, "min": 0.010504945743984232, "max": 0.023512957342124233, "count": 229 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017498819755079845, "min": 0.010504945743984232, "max": 0.023512957342124233, "count": 229 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 3.3816178965177336e-07, "min": 9.482979919835562e-10, "max": 0.06806231166119688, "count": 229 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 3.3816178965177336e-07, "min": 9.482979919835562e-10, "max": 0.06806231166119688, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 4.5237265264101246e-07, "min": 1.5800751966092244e-09, "max": 0.014206568882218561, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 4.5237265264101246e-07, "min": 1.5800751966092244e-09, "max": 0.014206568882218561, "count": 229 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 229 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 229 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694032223", "python_version": "3.9.5 (default, May 18 2021, 12:31:01) \n[Clang 10.0.0 ]", "command_line_arguments": "/usr/local/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --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", "numpy_version": "1.21.2", "end_time_seconds": "1694049686" }, "total": 17462.462335158998, "count": 1, "self": 0.5212547379996977, "children": { "run_training.setup": { "total": 0.027102105999999848, "count": 1, "self": 0.027102105999999848 }, "TrainerController.start_learning": { "total": 17461.913978315, "count": 1, "self": 6.82518092915052, "children": { "TrainerController._reset_env": { "total": 4.883682597997323, "count": 25, "self": 4.883682597997323 }, "TrainerController.advance": { "total": 17449.958925512852, "count": 325748, "self": 7.283867660538817, "children": { "env_step": { "total": 5403.73797770065, "count": 325748, "self": 4498.402953772352, "children": { "SubprocessEnvManager._take_step": { "total": 900.7566362351863, "count": 325748, "self": 39.27766881727416, "children": { "TorchPolicy.evaluate": { "total": 861.4789674179121, "count": 647500, "self": 861.4789674179121 } } }, "workers": { "total": 4.57838769311189, "count": 325748, "self": 0.0, "children": { "worker_root": { "total": 17446.325019702, "count": 325748, "is_parallel": true, "self": 13760.99144729516, "children": { "steps_from_proto": { "total": 0.056598513994616795, "count": 50, "is_parallel": true, "self": 0.011440272008518715, "children": { "_process_rank_one_or_two_observation": { "total": 0.04515824198609808, "count": 200, "is_parallel": true, "self": 0.04515824198609808 } } }, "UnityEnvironment.step": { "total": 3685.276973892844, "count": 325748, "is_parallel": true, "self": 183.38625784297528, "children": { "UnityEnvironment._generate_step_input": { "total": 114.61013622590804, "count": 325748, "is_parallel": true, "self": 114.61013622590804 }, "communicator.exchange": { "total": 2817.4277711418736, "count": 325748, "is_parallel": true, "self": 2817.4277711418736 }, "steps_from_proto": { "total": 569.8528086820874, "count": 651496, "is_parallel": true, "self": 112.00542663959783, "children": { "_process_rank_one_or_two_observation": { "total": 457.8473820424895, "count": 2605984, "is_parallel": true, "self": 457.8473820424895 } } } } } } } } } } }, "trainer_advance": { "total": 12038.937080151662, "count": 325748, "self": 46.84385535407091, "children": { "process_trajectory": { "total": 1396.0453400585836, "count": 325748, "self": 1392.7560748305814, "children": { "RLTrainer._checkpoint": { "total": 3.2892652280022503, "count": 10, "self": 3.2892652280022503 } } }, "_update_policy": { "total": 10596.047884739008, "count": 229, "self": 775.576012860096, "children": { "TorchPOCAOptimizer.update": { "total": 9820.471871878912, "count": 6870, "self": 9820.471871878912 } } } } } } }, "trainer_threads": { "total": 8.759998308960348e-07, "count": 1, "self": 8.759998308960348e-07 }, "TrainerController._save_models": { "total": 0.24618839899994782, "count": 1, "self": 0.0022777069971198216, "children": { "RLTrainer._checkpoint": { "total": 0.243910692002828, "count": 1, "self": 0.243910692002828 } } } } } } }