{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5024334192276, "min": 1.3184305429458618, "max": 3.295718193054199, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26731.294921875, "min": 14956.23828125, "max": 132043.515625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 92.11320754716981, "min": 37.651162790697676, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19528.0, "min": 14552.0, "max": 27504.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1541.1355558924997, "min": 1197.0158617313662, "max": 1688.5004096561183, "count": 4910 }, "SoccerTwos.Self-play.ELO.sum": { "value": 163360.36892460496, "min": 2395.238694786875, "max": 421624.67825181223, "count": 4910 }, "SoccerTwos.Step.mean": { "value": 49999964.0, "min": 9768.0, "max": 49999964.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999964.0, "min": 9768.0, "max": 49999964.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09638256579637527, "min": -0.1396932154893875, "max": 0.16838690638542175, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.216551780700684, "min": -25.325477600097656, "max": 22.267803192138672, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09742562472820282, "min": -0.14202383160591125, "max": 0.16969288885593414, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.327116012573242, "min": -25.125972747802734, "max": 22.327320098876953, "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": -0.2516566042630178, "min": -0.6363571413925716, "max": 0.5916088885731168, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -26.675600051879883, "min": -64.31119990348816, "max": 59.81119990348816, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2516566042630178, "min": -0.6363571413925716, "max": 0.5916088885731168, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -26.675600051879883, "min": -64.31119990348816, "max": 59.81119990348816, "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": 0.018697804305702448, "min": 0.009104452545579988, "max": 0.026643019893284266, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018697804305702448, "min": 0.009104452545579988, "max": 0.026643019893284266, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07356646607319514, "min": 2.9910259134643033e-07, "max": 0.12964732473095258, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07356646607319514, "min": 2.9910259134643033e-07, "max": 0.12964732473095258, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07455665295322736, "min": 3.0016980142969864e-07, "max": 0.13194423938790958, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07455665295322736, "min": 3.0016980142969864e-07, "max": 0.13194423938790958, "count": 2423 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694809363", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/gaionl/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695040180" }, "total": 230817.004368874, "count": 1, "self": 0.44111788604641333, "children": { "run_training.setup": { "total": 0.011371827000402845, "count": 1, "self": 0.011371827000402845 }, "TrainerController.start_learning": { "total": 230816.55187916098, "count": 1, "self": 85.74591592012439, "children": { "TrainerController._reset_env": { "total": 6.6357272081731935, "count": 250, "self": 6.6357272081731935 }, "TrainerController.advance": { "total": 230723.90142067865, "count": 3448206, "self": 91.43295751590631, "children": { "env_step": { "total": 72865.68168361404, "count": 3448206, "self": 61289.247190914786, "children": { "SubprocessEnvManager._take_step": { "total": 11522.558785983892, "count": 3448206, "self": 537.6852973723653, "children": { "TorchPolicy.evaluate": { "total": 10984.873488611527, "count": 6283316, "self": 10984.873488611527 } } }, "workers": { "total": 53.8757067153565, "count": 3448206, "self": 0.0, "children": { "worker_root": { "total": 230677.16631610927, "count": 3448206, "is_parallel": true, "self": 179001.27623207617, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035869470084435306, "count": 2, "is_parallel": true, "self": 0.0016239180040429346, "children": { "_process_rank_one_or_two_observation": { "total": 0.001963029004400596, "count": 8, "is_parallel": true, "self": 0.001963029004400596 } } }, "UnityEnvironment.step": { "total": 0.03157267300412059, "count": 1, "is_parallel": true, "self": 0.0010514200112083927, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008765649981796741, "count": 1, "is_parallel": true, "self": 0.0008765649981796741 }, "communicator.exchange": { "total": 0.026194890997430775, "count": 1, "is_parallel": true, "self": 0.026194890997430775 }, "steps_from_proto": { "total": 0.003449796997301746, "count": 2, "is_parallel": true, "self": 0.0006314890051726252, "children": { "_process_rank_one_or_two_observation": { "total": 0.002818307992129121, "count": 8, "is_parallel": true, "self": 0.002818307992129121 } } } } } } }, "UnityEnvironment.step": { "total": 51675.3453890593, "count": 3448205, "is_parallel": true, "self": 3156.6989525170357, "children": { "UnityEnvironment._generate_step_input": { "total": 2364.1434886952848, "count": 3448205, "is_parallel": true, "self": 2364.1434886952848 }, "communicator.exchange": { "total": 36481.022178212566, "count": 3448205, "is_parallel": true, "self": 36481.022178212566 }, "steps_from_proto": { "total": 9673.480769634414, "count": 6896410, "is_parallel": true, "self": 1761.7438183802733, "children": { "_process_rank_one_or_two_observation": { "total": 7911.736951254141, "count": 27585640, "is_parallel": true, "self": 7911.736951254141 } } } } }, "steps_from_proto": { "total": 0.5446949737961404, "count": 498, "is_parallel": true, "self": 0.10069432427553693, "children": { "_process_rank_one_or_two_observation": { "total": 0.4440006495206035, "count": 1992, "is_parallel": true, "self": 0.4440006495206035 } } } } } } } } }, "trainer_advance": { "total": 157766.7867795487, "count": 3448206, "self": 553.2083718009526, "children": { "process_trajectory": { "total": 14261.549504052033, "count": 3448206, "self": 14237.875778907168, "children": { "RLTrainer._checkpoint": { "total": 23.673725144864875, "count": 100, "self": 23.673725144864875 } } }, "_update_policy": { "total": 142952.02890369573, "count": 2423, "self": 8946.41707963511, "children": { "TorchPOCAOptimizer.update": { "total": 134005.61182406062, "count": 72690, "self": 134005.61182406062 } } } } } } }, "trainer_threads": { "total": 1.3430253602564335e-06, "count": 1, "self": 1.3430253602564335e-06 }, "TrainerController._save_models": { "total": 0.26881401101127267, "count": 1, "self": 0.00218809099169448, "children": { "RLTrainer._checkpoint": { "total": 0.2666259200195782, "count": 1, "self": 0.2666259200195782 } } } } } } }