{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.22209034860134125, "min": 0.20746326446533203, "max": 3.295814037322998, "count": 32000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 4917.96875, "min": 3382.24462890625, "max": 537455.0, "count": 32000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.8375, "min": 30.496815286624205, "max": 999.0, "count": 31999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18188.0, "min": 12154.0, "max": 31968.0, "count": 31999 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1295.1033099340552, "min": 1198.9833305085954, "max": 1526.593576735275, "count": 31998 }, "SoccerTwos.Self-play.ELO.sum": { "value": 209806.73620931694, "min": 4799.166576164476, "max": 459823.9773137702, "count": 31998 }, "SoccerTwos.Step.mean": { "value": 319999982.0, "min": 9814.0, "max": 319999982.0, "count": 32000 }, "SoccerTwos.Step.sum": { "value": 319999982.0, "min": 9814.0, "max": 319999982.0, "count": 32000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04039477929472923, "min": -0.14004386961460114, "max": 0.19318516552448273, "count": 32000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.02869176864624, "min": -33.47048568725586, "max": 44.917381286621094, "count": 32000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.040669914335012436, "min": -0.14202876389026642, "max": 0.19254568219184875, "count": 32000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.076564788818359, "min": -33.94487380981445, "max": 43.32111358642578, "count": 32000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 32000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 32000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.13182988797111073, "min": -0.4755161693710053, "max": 0.45742059236063676, "count": 32000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -22.938400506973267, "min": -84.72239971160889, "max": 80.98259991407394, "count": 32000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.13182988797111073, "min": -0.4755161693710053, "max": 0.45742059236063676, "count": 32000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -22.938400506973267, "min": -84.72239971160889, "max": 80.98259991407394, "count": 32000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 32000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 32000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01372652525678859, "min": 0.009824401157311513, "max": 0.02974080921073134, "count": 15523 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01372652525678859, "min": 0.009824401157311513, "max": 0.02974080921073134, "count": 15523 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0831478034456571, "min": 0.003702893130815564, "max": 0.09432442312439283, "count": 15523 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0831478034456571, "min": 0.003702893130815564, "max": 0.09432442312439283, "count": 15523 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08323371013005575, "min": 0.003703783314006451, "max": 0.09451528812448183, "count": 15523 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08323371013005575, "min": 0.003703783314006451, "max": 0.09451528812448183, "count": 15523 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 9.654059315318175e-09, "min": 9.654059315318175e-09, "max": 0.00029997494625835113, "count": 15523 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 9.654059315318175e-09, "min": 9.654059315318175e-09, "max": 0.00029997494625835113, "count": 15523 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 15523 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 15523 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.0318150281250186e-05, "min": 1.0318150281250186e-05, "max": 0.009999165710124998, "count": 15523 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.0318150281250186e-05, "min": 1.0318150281250186e-05, "max": 0.009999165710124998, "count": 15523 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693946942", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/mgmeskill/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=Downstrike-320M --no-graphics --num-envs=8", "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": "1694209087" }, "total": 262144.4315176448, "count": 1, "self": 0.27110950043424964, "children": { "run_training.setup": { "total": 0.02748629217967391, "count": 1, "self": 0.02748629217967391 }, "TrainerController.start_learning": { "total": 262144.1329218522, "count": 1, "self": 195.11936002317816, "children": { "TrainerController._reset_env": { "total": 1356.6803504824638, "count": 15631, "self": 1356.6803504824638 }, "TrainerController.advance": { "total": 260592.02951219212, "count": 5308235, "self": 61.60288550425321, "children": { "env_step": { "total": 260530.42662668787, "count": 5308235, "self": 85563.79976889957, "children": { "SubprocessEnvManager._take_step": { "total": 174811.16231037444, "count": 29456845, "self": 2541.197320862673, "children": { "TorchPolicy.evaluate": { "total": 172269.96498951176, "count": 53900846, "self": 172269.96498951176 } } }, "workers": { "total": 155.46454741386697, "count": 5308235, "self": 0.0, "children": { "worker_root": { "total": 2093413.5211095153, "count": 29425763, "is_parallel": true, "self": 1814096.7023123018, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.019203658681362867, "count": 16, "is_parallel": true, "self": 0.004011679440736771, "children": { "_process_rank_one_or_two_observation": { "total": 0.015191979240626097, "count": 64, "is_parallel": true, "self": 0.015191979240626097 } } }, "UnityEnvironment.step": { "total": 0.16575361602008343, "count": 8, "is_parallel": true, "self": 0.005824713036417961, "children": { "UnityEnvironment._generate_step_input": { "total": 0.004249729681760073, "count": 8, "is_parallel": true, "self": 0.004249729681760073 }, "communicator.exchange": { "total": 0.13958576088771224, "count": 8, "is_parallel": true, "self": 0.13958576088771224 }, "steps_from_proto": { "total": 0.016093412414193153, "count": 16, "is_parallel": true, "self": 0.0028776959516108036, "children": { "_process_rank_one_or_two_observation": { "total": 0.01321571646258235, "count": 64, "is_parallel": true, "self": 0.01321571646258235 } } } } } } }, "UnityEnvironment.step": { "total": 279010.91643110896, "count": 29425755, "is_parallel": true, "self": 17052.918171677273, "children": { "UnityEnvironment._generate_step_input": { "total": 11083.002196655609, "count": 29425755, "is_parallel": true, "self": 11083.002196655609 }, "communicator.exchange": { "total": 203583.36522475723, "count": 29425755, "is_parallel": true, "self": 203583.36522475723 }, "steps_from_proto": { "total": 47291.63083801884, "count": 58851510, "is_parallel": true, "self": 7972.866389919538, "children": { "_process_rank_one_or_two_observation": { "total": 39318.764448099304, "count": 235406040, "is_parallel": true, "self": 39318.764448099304 } } } } }, "steps_from_proto": { "total": 305.90236610453576, "count": 250080, "is_parallel": true, "self": 49.52144989045337, "children": { "_process_rank_one_or_two_observation": { "total": 256.3809162140824, "count": 1000320, "is_parallel": true, "self": 256.3809162140824 } } } } } } } } } } }, "trainer_threads": { "total": 3.0568335205316544e-05, "count": 1, "self": 3.0568335205316544e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 260611.0573132881, "count": 352518542, "is_parallel": true, "self": 9217.686727115884, "children": { "process_trajectory": { "total": 177371.24861753872, "count": 352518542, "is_parallel": true, "self": 177307.83409809368, "children": { "RLTrainer._checkpoint": { "total": 63.41451944503933, "count": 160, "is_parallel": true, "self": 63.41451944503933 } } }, "_update_policy": { "total": 74022.1219686335, "count": 15523, "is_parallel": true, "self": 38076.0070996345, "children": { "TorchPOCAOptimizer.update": { "total": 35946.11486899899, "count": 465699, "is_parallel": true, "self": 35946.11486899899 } } } } } } } } }, "TrainerController._save_models": { "total": 0.30366858607158065, "count": 1, "self": 0.001912000123411417, "children": { "RLTrainer._checkpoint": { "total": 0.30175658594816923, "count": 1, "self": 0.30175658594816923 } } } } } } }