{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.7428579330444336, "min": 2.437469244003296, "max": 3.1816556453704834, "count": 696 }, "SoccerTwos.Policy.Entropy.sum": { "value": 63722.078125, "min": 7536.775390625, "max": 129973.140625, "count": 696 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 140.55263157894737, "min": 140.55263157894737, "max": 999.0, "count": 696 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21364.0, "min": 5496.0, "max": 31968.0, "count": 696 }, "SoccerTwos.Step.mean": { "value": 9999782.0, "min": 3009612.0, "max": 9999782.0, "count": 700 }, "SoccerTwos.Step.sum": { "value": 9999782.0, "min": 3009612.0, "max": 9999782.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06505332142114639, "min": -0.05419081822037697, "max": 0.0902983620762825, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.87899923324585, "min": -1.3335270881652832, "max": 5.056708335876465, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06641251593828201, "min": -0.05656322091817856, "max": 0.08459983021020889, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.98093843460083, "min": -1.318099856376648, "max": 4.98093843460083, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.021770664056142173, "min": -0.6829000016053518, "max": 0.46457390875920007, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.6327998042106628, "min": -21.472000002861023, "max": 20.561199963092804, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.021770664056142173, "min": -0.6829000016053518, "max": 0.46457390875920007, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.6327998042106628, "min": -21.472000002861023, "max": 20.561199963092804, "count": 700 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01627806848361312, "min": 0.010313435654264442, "max": 0.0232652225192093, "count": 322 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01627806848361312, "min": 0.010313435654264442, "max": 0.0232652225192093, "count": 322 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.03741802188257377, "min": 5.280471230643494e-09, "max": 0.040542762354016305, "count": 322 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.03741802188257377, "min": 5.280471230643494e-09, "max": 0.040542762354016305, "count": 322 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.039657964805761975, "min": 1.3398230673071035e-08, "max": 0.043440181016922, "count": 322 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.039657964805761975, "min": 1.3398230673071035e-08, "max": 0.043440181016922, "count": 322 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 322 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 322 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 322 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 322 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 322 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 322 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1271.059761804736, "min": 1188.2032750442393, "max": 1271.059761804736, "count": 363 }, "SoccerTwos.Self-play.ELO.sum": { "value": 96600.54189715993, "min": 2376.4065500884785, "max": 96600.54189715993, "count": 363 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713882396", "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--10M --no-graphics --resume", "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": "1.22.0", "end_time_seconds": "1713888778" }, "total": 6381.440599580001, "count": 1, "self": 0.21899853000104486, "children": { "run_training.setup": { "total": 0.018660466999961045, "count": 1, "self": 0.018660466999961045 }, "TrainerController.start_learning": { "total": 6381.202940583, "count": 1, "self": 5.458867465060393, "children": { "TrainerController._reset_env": { "total": 3.310826252998652, "count": 36, "self": 3.310826252998652 }, "TrainerController.advance": { "total": 6372.31996542894, "count": 454308, "self": 5.944240250029907, "children": { "env_step": { "total": 4984.437968784959, "count": 454308, "self": 3799.086302090814, "children": { "SubprocessEnvManager._take_step": { "total": 1181.7706949170774, "count": 454308, "self": 41.30988718521985, "children": { "TorchPolicy.evaluate": { "total": 1140.4608077318576, "count": 900466, "self": 1140.4608077318576 } } }, "workers": { "total": 3.580971777067134, "count": 454308, "self": 0.0, "children": { "worker_root": { "total": 6370.69903301716, "count": 454308, "is_parallel": true, "self": 3292.2626059137747, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016655070000410888, "count": 2, "is_parallel": true, "self": 0.0005323700000872122, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011331369999538765, "count": 8, "is_parallel": true, "self": 0.0011331369999538765 } } }, "UnityEnvironment.step": { "total": 0.016068247000021074, "count": 1, "is_parallel": true, "self": 0.0003498739999940881, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025395700004082755, "count": 1, "is_parallel": true, "self": 0.00025395700004082755 }, "communicator.exchange": { "total": 0.014433295000003454, "count": 1, "is_parallel": true, "self": 0.014433295000003454 }, "steps_from_proto": { "total": 0.0010311209999827042, "count": 2, "is_parallel": true, "self": 0.00020024199994850278, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008308790000342015, "count": 8, "is_parallel": true, "self": 0.0008308790000342015 } } } } } } }, "steps_from_proto": { "total": 0.0530178039999214, "count": 70, "is_parallel": true, "self": 0.00998233799487025, "children": { "_process_rank_one_or_two_observation": { "total": 0.04303546600505115, "count": 280, "is_parallel": true, "self": 0.04303546600505115 } } }, "UnityEnvironment.step": { "total": 3078.3834092993857, "count": 454307, "is_parallel": true, "self": 169.00256565386826, "children": { "UnityEnvironment._generate_step_input": { "total": 101.70317954187209, "count": 454307, "is_parallel": true, "self": 101.70317954187209 }, "communicator.exchange": { "total": 2333.3211244147583, "count": 454307, "is_parallel": true, "self": 2333.3211244147583 }, "steps_from_proto": { "total": 474.3565396888869, "count": 908614, "is_parallel": true, "self": 86.2822359749614, "children": { "_process_rank_one_or_two_observation": { "total": 388.07430371392553, "count": 3634456, "is_parallel": true, "self": 388.07430371392553 } } } } } } } } } } }, "trainer_advance": { "total": 1381.937756393952, "count": 454308, "self": 50.25165036416024, "children": { "process_trajectory": { "total": 350.4816239237884, "count": 454308, "self": 348.7550255137881, "children": { "RLTrainer._checkpoint": { "total": 1.7265984100002925, "count": 14, "self": 1.7265984100002925 } } }, "_update_policy": { "total": 981.2044821060034, "count": 322, "self": 644.6803675179726, "children": { "TorchPOCAOptimizer.update": { "total": 336.5241145880307, "count": 9744, "self": 336.5241145880307 } } } } } } }, "trainer_threads": { "total": 6.750005923095159e-07, "count": 1, "self": 6.750005923095159e-07 }, "TrainerController._save_models": { "total": 0.11328076100016915, "count": 1, "self": 0.0012160260002929135, "children": { "RLTrainer._checkpoint": { "total": 0.11206473499987624, "count": 1, "self": 0.11206473499987624 } } } } } } }