{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.217785120010376, "min": 3.217785120010376, "max": 3.2957370281219482, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 77844.65625, "min": 30434.7265625, "max": 106996.515625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 814.1666666666666, "min": 425.3333333333333, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19540.0, "min": 11580.0, "max": 28944.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.044770602272, "min": 1195.9973883999355, "max": 1204.8377396759354, "count": 40 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4792.179082409088, "min": 2392.286360747513, "max": 14449.935628685635, "count": 40 }, "SoccerTwos.Step.mean": { "value": 499698.0, "min": 9492.0, "max": 499698.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499698.0, "min": 9492.0, "max": 499698.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0019286455353721976, "min": -0.013795465230941772, "max": 0.03413105010986328, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.023143745958805084, "min": -0.17934104800224304, "max": 0.5460968017578125, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0019079806515946984, "min": -0.014374150894582272, "max": 0.034138184040784836, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.02289576828479767, "min": -0.1868639588356018, "max": 0.5462109446525574, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3333333333333333, "min": -0.5813499987125397, "max": 0.2639384636512169, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.0, "min": -9.301599979400635, "max": 3.4312000274658203, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3333333333333333, "min": -0.5813499987125397, "max": 0.2639384636512169, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.0, "min": -9.301599979400635, "max": 3.4312000274658203, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019473070788323336, "min": 0.011850763300026301, "max": 0.020279537975632898, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019473070788323336, "min": 0.011850763300026301, "max": 0.020279537975632898, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0023729100978622836, "min": 0.0002559008765577649, "max": 0.005488590515839557, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0023729100978622836, "min": 0.0002559008765577649, "max": 0.005488590515839557, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0023844250904706617, "min": 0.00026136371307075026, "max": 0.005589628095428149, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0023844250904706617, "min": 0.00026136371307075026, "max": 0.005589628095428149, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715796622", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/devjwsong/huggingface-deep-rl-unit7/venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715797425" }, "total": 803.3842057170004, "count": 1, "self": 0.2203748860010819, "children": { "run_training.setup": { "total": 0.010151954999855661, "count": 1, "self": 0.010151954999855661 }, "TrainerController.start_learning": { "total": 803.1536788759995, "count": 1, "self": 0.5124147460232962, "children": { "TrainerController._reset_env": { "total": 1.3019092990002719, "count": 5, "self": 1.3019092990002719 }, "TrainerController.advance": { "total": 801.1647018709755, "count": 33600, "self": 0.5570670478991815, "children": { "env_step": { "total": 664.2272672040535, "count": 33600, "self": 427.1711559940363, "children": { "SubprocessEnvManager._take_step": { "total": 236.6911342440303, "count": 33600, "self": 3.1912772060641146, "children": { "TorchPolicy.evaluate": { "total": 233.4998570379662, "count": 66748, "self": 233.4998570379662 } } }, "workers": { "total": 0.364976965986898, "count": 33600, "self": 0.0, "children": { "worker_root": { "total": 801.4377628630186, "count": 33600, "is_parallel": true, "self": 432.7049865160038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003362260999438149, "count": 2, "is_parallel": true, "self": 0.0005453819999274856, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028168789995106636, "count": 8, "is_parallel": true, "self": 0.0028168789995106636 } } }, "UnityEnvironment.step": { "total": 0.01822538699980214, "count": 1, "is_parallel": true, "self": 0.00035461399966152385, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003073369998674025, "count": 1, "is_parallel": true, "self": 0.0003073369998674025 }, "communicator.exchange": { "total": 0.016526605000308336, "count": 1, "is_parallel": true, "self": 0.016526605000308336 }, "steps_from_proto": { "total": 0.0010368309999648773, "count": 2, "is_parallel": true, "self": 0.00022454100007962552, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008122899998852517, "count": 8, "is_parallel": true, "self": 0.0008122899998852517 } } } } } } }, "UnityEnvironment.step": { "total": 368.7288059720149, "count": 33599, "is_parallel": true, "self": 11.501609316109807, "children": { "UnityEnvironment._generate_step_input": { "total": 7.075339974986946, "count": 33599, "is_parallel": true, "self": 7.075339974986946 }, "communicator.exchange": { "total": 316.49461825203025, "count": 33599, "is_parallel": true, "self": 316.49461825203025 }, "steps_from_proto": { "total": 33.65723842888792, "count": 67198, "is_parallel": true, "self": 7.212224628861804, "children": { "_process_rank_one_or_two_observation": { "total": 26.445013800026118, "count": 268792, "is_parallel": true, "self": 26.445013800026118 } } } } }, "steps_from_proto": { "total": 0.0039703749998807325, "count": 8, "is_parallel": true, "self": 0.0008164830019268265, "children": { "_process_rank_one_or_two_observation": { "total": 0.003153891997953906, "count": 32, "is_parallel": true, "self": 0.003153891997953906 } } } } } } } } }, "trainer_advance": { "total": 136.38036761902276, "count": 33600, "self": 4.236921489100951, "children": { "process_trajectory": { "total": 54.43169432992272, "count": 33600, "self": 54.23925358892211, "children": { "RLTrainer._checkpoint": { "total": 0.1924407410006097, "count": 1, "self": 0.1924407410006097 } } }, "_update_policy": { "total": 77.71175179999909, "count": 23, "self": 33.563087567993534, "children": { "TorchPOCAOptimizer.update": { "total": 44.14866423200556, "count": 690, "self": 44.14866423200556 } } } } } } }, "trainer_threads": { "total": 5.649999366141856e-07, "count": 1, "self": 5.649999366141856e-07 }, "TrainerController._save_models": { "total": 0.1746523950005212, "count": 1, "self": 0.0012465290001273388, "children": { "RLTrainer._checkpoint": { "total": 0.17340586600039387, "count": 1, "self": 0.17340586600039387 } } } } } } }