{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3939404487609863, "min": 1.3719195127487183, "max": 3.2957265377044678, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25648.50390625, "min": 14878.703125, "max": 118678.4140625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.92857142857143, "min": 42.26086956521739, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19580.0, "min": 10440.0, "max": 29016.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1635.4828310086612, "min": 1187.7123070243715, "max": 1726.3880276739098, "count": 4758 }, "SoccerTwos.Self-play.ELO.sum": { "value": 228967.59634121257, "min": 2379.331272893961, "max": 385609.3104376043, "count": 4758 }, "SoccerTwos.Step.mean": { "value": 49999990.0, "min": 9480.0, "max": 49999990.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999990.0, "min": 9480.0, "max": 49999990.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.026236118748784065, "min": -0.1528344750404358, "max": 0.10606024414300919, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.646820545196533, "min": -24.4783935546875, "max": 17.445110321044922, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02696564793586731, "min": -0.1493614912033081, "max": 0.11085597425699234, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.748224973678589, "min": -25.425262451171875, "max": 18.17091178894043, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.03779712126409407, "min": -0.7162173911119285, "max": 0.5624260824659596, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.253799855709076, "min": -69.97099977731705, "max": 74.7530003786087, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.03779712126409407, "min": -0.7162173911119285, "max": 0.5624260824659596, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.253799855709076, "min": -69.97099977731705, "max": 74.7530003786087, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017735078521460914, "min": 0.008954473514071045, "max": 0.026522330838876465, "count": 2413 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017735078521460914, "min": 0.008954473514071045, "max": 0.026522330838876465, "count": 2413 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10043665369351705, "min": 3.6992200191932057e-09, "max": 0.12208863521615664, "count": 2413 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10043665369351705, "min": 3.6992200191932057e-09, "max": 0.12208863521615664, "count": 2413 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10179258162776629, "min": 4.900589356537921e-09, "max": 0.12400366912285486, "count": 2413 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10179258162776629, "min": 4.900589356537921e-09, "max": 0.12400366912285486, "count": 2413 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2413 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2413 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2413 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2413 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2413 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2413 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1720769132", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/hades/anaconda3/envs/RL2/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720805726" }, "total": 36593.61216562707, "count": 1, "self": 0.21711287705693394, "children": { "run_training.setup": { "total": 0.013519776985049248, "count": 1, "self": 0.013519776985049248 }, "TrainerController.start_learning": { "total": 36593.38153297303, "count": 1, "self": 31.63546387886163, "children": { "TrainerController._reset_env": { "total": 4.9099565368378535, "count": 250, "self": 4.9099565368378535 }, "TrainerController.advance": { "total": 36556.66296063631, "count": 3404602, "self": 35.32725452282466, "children": { "env_step": { "total": 28301.106583668618, "count": 3404602, "self": 22056.492698352435, "children": { "SubprocessEnvManager._take_step": { "total": 6223.310742922244, "count": 3404602, "self": 230.57538916682824, "children": { "TorchPolicy.evaluate": { "total": 5992.735353755415, "count": 6301114, "self": 5992.735353755415 } } }, "workers": { "total": 21.303142393939197, "count": 3404602, "self": 0.0, "children": { "worker_root": { "total": 36545.58726854413, "count": 3404602, "is_parallel": true, "self": 18193.655372003675, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011534460354596376, "count": 2, "is_parallel": true, "self": 0.0002857443178072572, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008677017176523805, "count": 8, "is_parallel": true, "self": 0.0008677017176523805 } } }, "UnityEnvironment.step": { "total": 0.012876980006694794, "count": 1, "is_parallel": true, "self": 0.0003187499241903424, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000208204030059278, "count": 1, "is_parallel": true, "self": 0.000208204030059278 }, "communicator.exchange": { "total": 0.011542862979695201, "count": 1, "is_parallel": true, "self": 0.011542862979695201 }, "steps_from_proto": { "total": 0.0008071630727499723, "count": 2, "is_parallel": true, "self": 0.00016571104060858488, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006414520321413875, "count": 8, "is_parallel": true, "self": 0.0006414520321413875 } } } } } } }, "UnityEnvironment.step": { "total": 18351.70103925839, "count": 3404601, "is_parallel": true, "self": 998.097620257875, "children": { "UnityEnvironment._generate_step_input": { "total": 701.1515328927198, "count": 3404601, "is_parallel": true, "self": 701.1515328927198 }, "communicator.exchange": { "total": 13929.12562271289, "count": 3404601, "is_parallel": true, "self": 13929.12562271289 }, "steps_from_proto": { "total": 2723.3262633949053, "count": 6809202, "is_parallel": true, "self": 528.2656808742322, "children": { "_process_rank_one_or_two_observation": { "total": 2195.060582520673, "count": 27236808, "is_parallel": true, "self": 2195.060582520673 } } } } }, "steps_from_proto": { "total": 0.23085728206206113, "count": 498, "is_parallel": true, "self": 0.04691020573955029, "children": { "_process_rank_one_or_two_observation": { "total": 0.18394707632251084, "count": 1992, "is_parallel": true, "self": 0.18394707632251084 } } } } } } } } }, "trainer_advance": { "total": 8220.22912244487, "count": 3404602, "self": 281.1879498139024, "children": { "process_trajectory": { "total": 3357.9068866183516, "count": 3404602, "self": 3339.1233077220386, "children": { "RLTrainer._checkpoint": { "total": 18.783578896312974, "count": 100, "self": 18.783578896312974 } } }, "_update_policy": { "total": 4581.134286012617, "count": 2413, "self": 2621.4029518801253, "children": { "TorchPOCAOptimizer.update": { "total": 1959.7313341324916, "count": 72393, "self": 1959.7313341324916 } } } } } } }, "trainer_threads": { "total": 4.200264811515808e-07, "count": 1, "self": 4.200264811515808e-07 }, "TrainerController._save_models": { "total": 0.17315150098875165, "count": 1, "self": 0.0009437069529667497, "children": { "RLTrainer._checkpoint": { "total": 0.1722077940357849, "count": 1, "self": 0.1722077940357849 } } } } } } }