{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4069026708602905, "min": 1.29377281665802, "max": 3.295738458633423, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28543.2421875, "min": 22218.025390625, "max": 120706.78125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.2394366197183, "min": 40.49586776859504, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19380.0, "min": 11988.0, "max": 27860.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1499.4810805536442, "min": 1195.0124214592158, "max": 1621.4621773364481, "count": 4995 }, "SoccerTwos.Self-play.ELO.sum": { "value": 212926.31343861748, "min": 2390.6177096129736, "max": 373540.5610917134, "count": 4995 }, "SoccerTwos.Step.mean": { "value": 49999986.0, "min": 9948.0, "max": 49999986.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999986.0, "min": 9948.0, "max": 49999986.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.019215716049075127, "min": -0.1476471722126007, "max": 0.14739100635051727, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.7286317348480225, "min": -26.892528533935547, "max": 22.279094696044922, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.021505970507860184, "min": -0.14920662343502045, "max": 0.14208893477916718, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.0538477897644043, "min": -27.792810440063477, "max": 21.318920135498047, "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": 0.19399155193651227, "min": -0.7333333333333333, "max": 0.4696700040251017, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 27.54680037498474, "min": -74.42199993133545, "max": 56.98079991340637, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.19399155193651227, "min": -0.7333333333333333, "max": 0.4696700040251017, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 27.54680037498474, "min": -74.42199993133545, "max": 56.98079991340637, "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": 0.01577753465123048, "min": 0.010905576529330574, "max": 0.029507850762456656, "count": 2425 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01577753465123048, "min": 0.010905576529330574, "max": 0.029507850762456656, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10188633650541305, "min": 5.8236272889189425e-05, "max": 0.12530214041471482, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10188633650541305, "min": 5.8236272889189425e-05, "max": 0.12530214041471482, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10280163586139679, "min": 6.122459805434725e-05, "max": 0.1268143229186535, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10280163586139679, "min": 6.122459805434725e-05, "max": 0.1268143229186535, "count": 2425 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684689787", "python_version": "3.9.16 (main, Dec 7 2022, 01:12:08) \n[GCC 11.3.0]", "command_line_arguments": "/home/wasim/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1684767561" }, "total": 77774.623135834, "count": 1, "self": 0.26933160300541203, "children": { "run_training.setup": { "total": 0.033267454000451835, "count": 1, "self": 0.033267454000451835 }, "TrainerController.start_learning": { "total": 77774.320536777, "count": 1, "self": 66.66508520353818, "children": { "TrainerController._reset_env": { "total": 8.8151817979724, "count": 250, "self": 8.8151817979724 }, "TrainerController.advance": { "total": 77698.65109348748, "count": 3438105, "self": 72.97681465253117, "children": { "env_step": { "total": 57792.64563782724, "count": 3438105, "self": 45403.03558742163, "children": { "SubprocessEnvManager._take_step": { "total": 12345.760968986491, "count": 3438105, "self": 336.45874955991894, "children": { "TorchPolicy.evaluate": { "total": 12009.302219426572, "count": 6279864, "self": 12009.302219426572 } } }, "workers": { "total": 43.849081419116374, "count": 3438105, "self": 0.0, "children": { "worker_root": { "total": 77689.86328874431, "count": 3438105, "is_parallel": true, "self": 39875.796183866536, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020441939996089786, "count": 2, "is_parallel": true, "self": 0.0005743729989262647, "children": { "_process_rank_one_or_two_observation": { "total": 0.001469821000682714, "count": 8, "is_parallel": true, "self": 0.001469821000682714 } } }, "UnityEnvironment.step": { "total": 0.02816668800005573, "count": 1, "is_parallel": true, "self": 0.0004654609992940095, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003511559998514713, "count": 1, "is_parallel": true, "self": 0.0003511559998514713 }, "communicator.exchange": { "total": 0.025915679000718228, "count": 1, "is_parallel": true, "self": 0.025915679000718228 }, "steps_from_proto": { "total": 0.0014343920001920196, "count": 2, "is_parallel": true, "self": 0.00030451800012087915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011298740000711405, "count": 8, "is_parallel": true, "self": 0.0011298740000711405 } } } } } } }, "UnityEnvironment.step": { "total": 37813.65709725354, "count": 3438104, "is_parallel": true, "self": 2219.563376553335, "children": { "UnityEnvironment._generate_step_input": { "total": 1154.0915136295525, "count": 3438104, "is_parallel": true, "self": 1154.0915136295525 }, "communicator.exchange": { "total": 28902.245302011746, "count": 3438104, "is_parallel": true, "self": 28902.245302011746 }, "steps_from_proto": { "total": 5537.756905058908, "count": 6876208, "is_parallel": true, "self": 1055.812628333947, "children": { "_process_rank_one_or_two_observation": { "total": 4481.944276724961, "count": 27504832, "is_parallel": true, "self": 4481.944276724961 } } } } }, "steps_from_proto": { "total": 0.4100076242339128, "count": 498, "is_parallel": true, "self": 0.07773165151411376, "children": { "_process_rank_one_or_two_observation": { "total": 0.33227597271979903, "count": 1992, "is_parallel": true, "self": 0.33227597271979903 } } } } } } } } }, "trainer_advance": { "total": 19833.028641007717, "count": 3438105, "self": 438.8399198807674, "children": { "process_trajectory": { "total": 7209.140279734995, "count": 3438105, "self": 7190.487030254943, "children": { "RLTrainer._checkpoint": { "total": 18.653249480051272, "count": 100, "self": 18.653249480051272 } } }, "_update_policy": { "total": 12185.048441391955, "count": 2425, "self": 5776.114478957434, "children": { "TorchPOCAOptimizer.update": { "total": 6408.933962434521, "count": 72756, "self": 6408.933962434521 } } } } } } }, "trainer_threads": { "total": 6.760092219337821e-07, "count": 1, "self": 6.760092219337821e-07 }, "TrainerController._save_models": { "total": 0.1891756120021455, "count": 1, "self": 0.0013836040016030893, "children": { "RLTrainer._checkpoint": { "total": 0.1877920080005424, "count": 1, "self": 0.1877920080005424 } } } } } } }