{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7817800045013428, "min": 1.7250133752822876, "max": 3.295700788497925, "count": 1052 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34723.328125, "min": 21780.318359375, "max": 133069.140625, "count": 1052 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.47727272727273, "min": 43.464285714285715, "max": 999.0, "count": 1052 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19528.0, "min": 12216.0, "max": 28964.0, "count": 1052 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1632.5894626924967, "min": 1191.887020798648, "max": 1648.8404105809843, "count": 977 }, "SoccerTwos.Self-play.ELO.sum": { "value": 287335.74543387943, "min": 2383.774041597296, "max": 362684.33966475364, "count": 977 }, "SoccerTwos.Step.mean": { "value": 10519948.0, "min": 9498.0, "max": 10519948.0, "count": 1052 }, "SoccerTwos.Step.sum": { "value": 10519948.0, "min": 9498.0, "max": 10519948.0, "count": 1052 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04358692094683647, "min": -0.12358210980892181, "max": 0.17494754493236542, "count": 1052 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.714885234832764, "min": -23.974929809570312, "max": 24.941734313964844, "count": 1052 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03762010112404823, "min": -0.12642516195774078, "max": 0.1727839708328247, "count": 1052 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.658758163452148, "min": -24.52648162841797, "max": 24.625225067138672, "count": 1052 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1052 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1052 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.02066440804529998, "min": -0.5454545454545454, "max": 0.5295538489635174, "count": 1052 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.657600224018097, "min": -63.27639985084534, "max": 58.7440003156662, "count": 1052 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.02066440804529998, "min": -0.5454545454545454, "max": 0.5295538489635174, "count": 1052 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.657600224018097, "min": -63.27639985084534, "max": 58.7440003156662, "count": 1052 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1052 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1052 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014275110346109917, "min": 0.010201355783889691, "max": 0.025112788159943496, "count": 504 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014275110346109917, "min": 0.010201355783889691, "max": 0.025112788159943496, "count": 504 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1174595611790816, "min": 2.510311603032278e-07, "max": 0.12384543816248576, "count": 504 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1174595611790816, "min": 2.510311603032278e-07, "max": 0.12384543816248576, "count": 504 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11924019828438759, "min": 2.5207407882514115e-07, "max": 0.12669917717576026, "count": 504 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11924019828438759, "min": 2.5207407882514115e-07, "max": 0.12669917717576026, "count": 504 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 504 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 504 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 504 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 504 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 504 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 504 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713926566", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/robot/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-base-15M --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713936409" }, "total": 9843.115602129, "count": 1, "self": 0.0695221420028247, "children": { "run_training.setup": { "total": 0.01935449699885794, "count": 1, "self": 0.01935449699885794 }, "TrainerController.start_learning": { "total": 9843.026725489999, "count": 1, "self": 8.712747135738027, "children": { "TrainerController._reset_env": { "total": 2.2645079790017917, "count": 53, "self": 2.2645079790017917 }, "TrainerController.advance": { "total": 9831.901042269263, "count": 713878, "self": 9.24496852802804, "children": { "env_step": { "total": 7510.175283239212, "count": 713878, "self": 5466.3694888746595, "children": { "SubprocessEnvManager._take_step": { "total": 2037.926973119651, "count": 713878, "self": 63.34080995932163, "children": { "TorchPolicy.evaluate": { "total": 1974.5861631603293, "count": 1330472, "self": 1974.5861631603293 } } }, "workers": { "total": 5.878821244901701, "count": 713877, "self": 0.0, "children": { "worker_root": { "total": 9831.54576087451, "count": 713877, "is_parallel": true, "self": 5438.992713308098, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001504736001152196, "count": 2, "is_parallel": true, "self": 0.00035498300167091656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011497529994812794, "count": 8, "is_parallel": true, "self": 0.0011497529994812794 } } }, "UnityEnvironment.step": { "total": 0.017274275998715893, "count": 1, "is_parallel": true, "self": 0.0003734840011020424, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027335800041328184, "count": 1, "is_parallel": true, "self": 0.00027335800041328184 }, "communicator.exchange": { "total": 0.015498355998715851, "count": 1, "is_parallel": true, "self": 0.015498355998715851 }, "steps_from_proto": { "total": 0.0011290779984847177, "count": 2, "is_parallel": true, "self": 0.00021096100135764573, "children": { "_process_rank_one_or_two_observation": { "total": 0.000918116997127072, "count": 8, "is_parallel": true, "self": 0.000918116997127072 } } } } } } }, "UnityEnvironment.step": { "total": 4392.494183618404, "count": 713876, "is_parallel": true, "self": 253.6064293788113, "children": { "UnityEnvironment._generate_step_input": { "total": 152.94743141446634, "count": 713876, "is_parallel": true, "self": 152.94743141446634 }, "communicator.exchange": { "total": 3302.750219678226, "count": 713876, "is_parallel": true, "self": 3302.750219678226 }, "steps_from_proto": { "total": 683.1901031469006, "count": 1427752, "is_parallel": true, "self": 127.8360065082561, "children": { "_process_rank_one_or_two_observation": { "total": 555.3540966386445, "count": 5711008, "is_parallel": true, "self": 555.3540966386445 } } } } }, "steps_from_proto": { "total": 0.05886394800654671, "count": 104, "is_parallel": true, "self": 0.011245435985983931, "children": { "_process_rank_one_or_two_observation": { "total": 0.047618512020562775, "count": 416, "is_parallel": true, "self": 0.047618512020562775 } } } } } } } } }, "trainer_advance": { "total": 2312.4807905020225, "count": 713877, "self": 70.74629147308406, "children": { "process_trajectory": { "total": 916.004298510934, "count": 713877, "self": 913.4258434989388, "children": { "RLTrainer._checkpoint": { "total": 2.5784550119951746, "count": 21, "self": 2.5784550119951746 } } }, "_update_policy": { "total": 1325.7302005180045, "count": 505, "self": 741.9853737448902, "children": { "TorchPOCAOptimizer.update": { "total": 583.7448267731143, "count": 15150, "self": 583.7448267731143 } } } } } } }, "trainer_threads": { "total": 6.689988367725164e-07, "count": 1, "self": 6.689988367725164e-07 }, "TrainerController._save_models": { "total": 0.14842743699773564, "count": 1, "self": 0.0010613710001052823, "children": { "RLTrainer._checkpoint": { "total": 0.14736606599763036, "count": 1, "self": 0.14736606599763036 } } } } } } }