{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": -3.576278402306343e-07, "min": -3.576278402306343e-07, "max": 2.6939635276794434, "count": 836 }, "SoccerTwos.Policy.Entropy.sum": { "value": -0.005069732200354338, "min": -0.013641356490552425, "max": 84429.03125, "count": 836 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 459.3333333333333, "max": 999.0, "count": 836 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 11024.0, "max": 31704.0, "count": 836 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1156.9462840677766, "min": 1156.9462840677766, "max": 1200.0797527907453, "count": 63 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4627.785136271106, "min": 2320.753618686611, "max": 11989.95732238514, "count": 63 }, "SoccerTwos.Step.mean": { "value": 8359860.0, "min": 9522.0, "max": 8359860.0, "count": 836 }, "SoccerTwos.Step.sum": { "value": 8359860.0, "min": 9522.0, "max": 8359860.0, "count": 836 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.5491425395011902, "min": -13112.5654296875, "max": 8993.1416015625, "count": 836 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.491425514221191, "min": -200188.71875, "max": 89931.4140625, "count": 836 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.5343278050422668, "min": -12266.4697265625, "max": 8313.759765625, "count": 836 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.343277931213379, "min": -191058.328125, "max": 83137.59375, "count": 836 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 836 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 836 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5333333333333333, "max": 0.13266666730244955, "count": 836 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 1.5920000076293945, "count": 836 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5333333333333333, "max": 0.13266666730244955, "count": 836 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 1.5920000076293945, "count": 836 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 836 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 836 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018108418878788748, "min": 0.010324261578110358, "max": 0.3402867207924525, "count": 382 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018108418878788748, "min": 0.010324261578110358, "max": 0.3402867207924525, "count": 382 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 170.31988499959309, "min": 0.022363464161753655, "max": 148730041.06666666, "count": 382 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 170.31988499959309, "min": 0.022363464161753655, "max": 148730041.06666666, "count": 382 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 176.16862080891926, "min": 0.022276258375495673, "max": 157164864.53333333, "count": 382 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 176.16862080891926, "min": 0.022276258375495673, "max": 157164864.53333333, "count": 382 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0006269649854335752, "min": 0.0006269649854335752, "max": 0.0006998200650257049, "count": 382 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0006269649854335752, "min": 0.0006269649854335752, "max": 0.0006998200650257049, "count": 382 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.18956642499999996, "min": 0.18956642499999996, "max": 0.19997429499999994, "count": 382 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.18956642499999996, "min": 0.18956642499999996, "max": 0.19997429499999994, "count": 382 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0044793646074999995, "min": 0.0044793646074999995, "max": 0.0049987173205, "count": 382 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0044793646074999995, "min": 0.0044793646074999995, "max": 0.0049987173205, "count": 382 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723398286", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\manug\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1723479190" }, "total": 80903.70793779999, "count": 1, "self": 2.069925699994201, "children": { "run_training.setup": { "total": 0.15105419999963487, "count": 1, "self": 0.15105419999963487 }, "TrainerController.start_learning": { "total": 80901.4869579, "count": 1, "self": 20.6864982972329, "children": { "TrainerController._reset_env": { "total": 11.717578799991315, "count": 42, "self": 11.717578799991315 }, "TrainerController.advance": { "total": 80868.78792820277, "count": 544781, "self": 20.808423901471542, "children": { "env_step": { "total": 17379.407285900703, "count": 544781, "self": 11370.672526601464, "children": { "SubprocessEnvManager._take_step": { "total": 5995.216470601548, "count": 544781, "self": 144.72061600046527, "children": { "TorchPolicy.evaluate": { "total": 5850.495854601083, "count": 1081688, "self": 5850.495854601083 } } }, "workers": { "total": 13.518288697690878, "count": 544780, "self": 0.0, "children": { "worker_root": { "total": 80868.26328919677, "count": 544780, "is_parallel": true, "self": 72190.79113669817, "children": { "steps_from_proto": { "total": 0.10491680002451176, "count": 84, "is_parallel": true, "self": 0.021791200074403605, "children": { "_process_rank_one_or_two_observation": { "total": 0.08312559995010815, "count": 336, "is_parallel": true, "self": 0.08312559995010815 } } }, "UnityEnvironment.step": { "total": 8677.367235698575, "count": 544780, "is_parallel": true, "self": 525.3884943943776, "children": { "UnityEnvironment._generate_step_input": { "total": 504.18722250334486, "count": 544780, "is_parallel": true, "self": 504.18722250334486 }, "communicator.exchange": { "total": 5963.867111395936, "count": 544780, "is_parallel": true, "self": 5963.867111395936 }, "steps_from_proto": { "total": 1683.9244074049166, "count": 1089560, "is_parallel": true, "self": 345.08360731093126, "children": { "_process_rank_one_or_two_observation": { "total": 1338.8408000939853, "count": 4358240, "is_parallel": true, "self": 1338.8408000939853 } } } } } } } } } } }, "trainer_advance": { "total": 63468.57221840059, "count": 544780, "self": 151.92435729738645, "children": { "process_trajectory": { "total": 7092.484537903309, "count": 544780, "self": 7088.646304903301, "children": { "RLTrainer._checkpoint": { "total": 3.8382330000076763, "count": 16, "self": 3.8382330000076763 } } }, "_update_policy": { "total": 56224.1633231999, "count": 382, "self": 1967.5510151998606, "children": { "TorchPOCAOptimizer.update": { "total": 54256.61230800004, "count": 11469, "self": 54256.61230800004 } } } } } } }, "trainer_threads": { "total": 2.0000006770715117e-06, "count": 1, "self": 2.0000006770715117e-06 }, "TrainerController._save_models": { "total": 0.2949506000004476, "count": 1, "self": 0.01603400000021793, "children": { "RLTrainer._checkpoint": { "total": 0.27891660000022966, "count": 1, "self": 0.27891660000022966 } } } } } } }