{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.420534610748291, "min": 1.3608125448226929, "max": 1.570000410079956, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28047.03515625, "min": 24803.060546875, "max": 35913.1640625, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.12359550561798, "min": 44.77570093457944, "max": 108.17391304347827, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19624.0, "min": 18428.0, "max": 21000.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1878.768103515365, "min": 1795.837418342268, "max": 1901.145235982328, "count": 1000 }, "SoccerTwos.Self-play.ELO.sum": { "value": 334420.722425735, "min": 171269.35675982942, "max": 404701.20162605366, "count": 1000 }, "SoccerTwos.Step.mean": { "value": 39999989.0, "min": 30009878.0, "max": 39999989.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 39999989.0, "min": 30009878.0, "max": 39999989.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0312940739095211, "min": -0.14125216007232666, "max": 0.073383629322052, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.570344924926758, "min": -24.784133911132812, "max": 10.934160232543945, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.028624339029192924, "min": -0.1449059545993805, "max": 0.07165231555700302, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.095132350921631, "min": -25.281543731689453, "max": 10.67619514465332, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.029853929964344154, "min": -0.4508974802594225, "max": 0.3219466656446457, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.313999533653259, "min": -68.66480004787445, "max": 40.91879975795746, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.029853929964344154, "min": -0.4508974802594225, "max": 0.3219466656446457, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.313999533653259, "min": -68.66480004787445, "max": 40.91879975795746, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016824491468529837, "min": 0.010678941572162632, "max": 0.02459868296670417, "count": 485 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016824491468529837, "min": 0.010678941572162632, "max": 0.02459868296670417, "count": 485 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11973893319567044, "min": 0.07159942711393039, "max": 0.12052511448661486, "count": 485 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11973893319567044, "min": 0.07159942711393039, "max": 0.12052511448661486, "count": 485 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12087501386801401, "min": 0.07310381432374319, "max": 0.12231633613506952, "count": 485 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12087501386801401, "min": 0.07310381432374319, "max": 0.12231633613506952, "count": 485 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 485 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 485 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 485 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 485 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 485 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 485 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676013011", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/sasha/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume", "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": "1676059019" }, "total": 43520.903187742, "count": 1, "self": 1.4724713479954517, "children": { "run_training.setup": { "total": 0.026028468999999888, "count": 1, "self": 0.026028468999999888 }, "TrainerController.start_learning": { "total": 43519.404687925, "count": 1, "self": 16.958283389649296, "children": { "TrainerController._reset_env": { "total": 3.045327290983835, "count": 41, "self": 3.045327290983835 }, "TrainerController.advance": { "total": 43499.19516348536, "count": 687899, "self": 18.614015010607545, "children": { "env_step": { "total": 10792.059126881395, "count": 687899, "self": 8719.799770878757, "children": { "SubprocessEnvManager._take_step": { "total": 2061.966871777601, "count": 687899, "self": 82.47859382463957, "children": { "TorchPolicy.evaluate": { "total": 1979.4882779529617, "count": 1253924, "self": 1979.4882779529617 } } }, "workers": { "total": 10.292484225036375, "count": 687899, "self": 0.0, "children": { "worker_root": { "total": 43486.1855561065, "count": 687899, "is_parallel": true, "self": 36462.65928638144, "children": { "steps_from_proto": { "total": 0.07384253300281118, "count": 82, "is_parallel": true, "self": 0.016496121003803488, "children": { "_process_rank_one_or_two_observation": { "total": 0.057346411999007696, "count": 328, "is_parallel": true, "self": 0.057346411999007696 } } }, "UnityEnvironment.step": { "total": 7023.4524271920645, "count": 687899, "is_parallel": true, "self": 436.16573743886875, "children": { "UnityEnvironment._generate_step_input": { "total": 274.88153573949893, "count": 687899, "is_parallel": true, "self": 274.88153573949893 }, "communicator.exchange": { "total": 5136.899167271001, "count": 687899, "is_parallel": true, "self": 5136.899167271001 }, "steps_from_proto": { "total": 1175.5059867426962, "count": 1375798, "is_parallel": true, "self": 258.93821506038717, "children": { "_process_rank_one_or_two_observation": { "total": 916.5677716823091, "count": 5503192, "is_parallel": true, "self": 916.5677716823091 } } } } } } } } } } }, "trainer_advance": { "total": 32688.52202159336, "count": 687899, "self": 130.86425984039306, "children": { "process_trajectory": { "total": 3464.5631697249946, "count": 687899, "self": 3460.3678304699806, "children": { "RLTrainer._checkpoint": { "total": 4.1953392550142325, "count": 20, "self": 4.1953392550142325 } } }, "_update_policy": { "total": 29093.09459202797, "count": 485, "self": 1479.1673009769256, "children": { "TorchPOCAOptimizer.update": { "total": 27613.927291051044, "count": 14550, "self": 27613.927291051044 } } } } } } }, "trainer_threads": { "total": 9.840005077421665e-07, "count": 1, "self": 9.840005077421665e-07 }, "TrainerController._save_models": { "total": 0.2059127750035259, "count": 1, "self": 0.0029265910052345134, "children": { "RLTrainer._checkpoint": { "total": 0.20298618399829138, "count": 1, "self": 0.20298618399829138 } } } } } } }