{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.149009943008423, "min": 3.0920655727386475, "max": 3.295755386352539, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57639.4765625, "min": 17742.544921875, "max": 123030.3515625, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 419.9230769230769, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 11988.0, "max": 28196.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.1405668605373, "min": 1194.6627015140439, "max": 1204.034278640044, "count": 73 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2394.2811337210746, "min": 2392.647101577426, "max": 16821.98242286591, "count": 73 }, "SoccerTwos.Step.mean": { "value": 999986.0, "min": 9116.0, "max": 999986.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999986.0, "min": 9116.0, "max": 999986.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.002587884897366166, "min": -0.03601016849279404, "max": 0.005797781050205231, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.025878848508000374, "min": -0.5041423439979553, "max": 0.07835473120212555, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0025931489653885365, "min": -0.039575692266225815, "max": 0.005782643333077431, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.02593148872256279, "min": -0.5540596842765808, "max": 0.07517436146736145, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5625, "max": 0.3017142776932035, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -9.0, "max": 4.223999887704849, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5625, "max": 0.3017142776932035, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -9.0, "max": 4.223999887704849, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0168987456165875, "min": 0.012042445930031438, "max": 0.02239705673904003, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0168987456165875, "min": 0.012042445930031438, "max": 0.02239705673904003, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.000625235964738143, "min": 4.422941644103654e-06, "max": 0.007038854543740551, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.000625235964738143, "min": 4.422941644103654e-06, "max": 0.007038854543740551, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0006257908535189927, "min": 4.599396841816391e-06, "max": 0.0070884921588003635, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0006257908535189927, "min": 4.599396841816391e-06, "max": 0.0070884921588003635, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699443423", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=/content/ml-agents/training-envs-executables/linux/SoccerTwos --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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699445605" }, "total": 2181.160465174, "count": 1, "self": 0.42680890199972055, "children": { "run_training.setup": { "total": 0.0681738690000202, "count": 1, "self": 0.0681738690000202 }, "TrainerController.start_learning": { "total": 2180.665482403, "count": 1, "self": 1.482598219130523, "children": { "TrainerController._reset_env": { "total": 4.778055871999641, "count": 5, "self": 4.778055871999641 }, "TrainerController.advance": { "total": 2174.1929239598703, "count": 64922, "self": 1.6057936520119256, "children": { "env_step": { "total": 1780.3524618128895, "count": 64922, "self": 1369.766810939087, "children": { "SubprocessEnvManager._take_step": { "total": 409.6754709328279, "count": 64922, "self": 10.97205778098487, "children": { "TorchPolicy.evaluate": { "total": 398.70341315184305, "count": 129046, "self": 398.70341315184305 } } }, "workers": { "total": 0.9101799409745581, "count": 64922, "self": 0.0, "children": { "worker_root": { "total": 2176.474749460971, "count": 64922, "is_parallel": true, "self": 1019.283098851889, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004532323999228538, "count": 2, "is_parallel": true, "self": 0.0010208789999524015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0035114449992761365, "count": 8, "is_parallel": true, "self": 0.0035114449992761365 } } }, "UnityEnvironment.step": { "total": 0.03913147999992361, "count": 1, "is_parallel": true, "self": 0.001174363998870831, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000787323000622564, "count": 1, "is_parallel": true, "self": 0.000787323000622564 }, "communicator.exchange": { "total": 0.03343747400049324, "count": 1, "is_parallel": true, "self": 0.03343747400049324 }, "steps_from_proto": { "total": 0.003732318999936979, "count": 2, "is_parallel": true, "self": 0.0007477830013158382, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029845359986211406, "count": 8, "is_parallel": true, "self": 0.0029845359986211406 } } } } } } }, "UnityEnvironment.step": { "total": 1157.181611549082, "count": 64921, "is_parallel": true, "self": 75.01715701136709, "children": { "UnityEnvironment._generate_step_input": { "total": 48.206555096093325, "count": 64921, "is_parallel": true, "self": 48.206555096093325 }, "communicator.exchange": { "total": 806.254951789816, "count": 64921, "is_parallel": true, "self": 806.254951789816 }, "steps_from_proto": { "total": 227.70294765180552, "count": 129842, "is_parallel": true, "self": 36.63705008140914, "children": { "_process_rank_one_or_two_observation": { "total": 191.06589757039637, "count": 519368, "is_parallel": true, "self": 191.06589757039637 } } } } }, "steps_from_proto": { "total": 0.010039060000053723, "count": 8, "is_parallel": true, "self": 0.0018889550001404132, "children": { "_process_rank_one_or_two_observation": { "total": 0.00815010499991331, "count": 32, "is_parallel": true, "self": 0.00815010499991331 } } } } } } } } }, "trainer_advance": { "total": 392.2346684949689, "count": 64922, "self": 14.265407442085234, "children": { "process_trajectory": { "total": 105.45076121288639, "count": 64922, "self": 104.89955790788736, "children": { "RLTrainer._checkpoint": { "total": 0.551203304999035, "count": 2, "self": 0.551203304999035 } } }, "_update_policy": { "total": 272.5184998399973, "count": 46, "self": 164.45873168098115, "children": { "TorchPOCAOptimizer.update": { "total": 108.05976815901613, "count": 1383, "self": 108.05976815901613 } } } } } } }, "trainer_threads": { "total": 9.99999429041054e-07, "count": 1, "self": 9.99999429041054e-07 }, "TrainerController._save_models": { "total": 0.2119033520002631, "count": 1, "self": 0.0022559970002475893, "children": { "RLTrainer._checkpoint": { "total": 0.20964735500001552, "count": 1, "self": 0.20964735500001552 } } } } } } }