{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.0931687355041504, "min": 3.0931687355041504, "max": 3.285083770751953, "count": 20 }, "SoccerTwos.Policy.Entropy.sum": { "value": 318126.21875, "min": 295396.78125, "max": 392512.96875, "count": 20 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 905.2142857142857, "min": 742.5151515151515, "max": 964.2692307692307, "count": 20 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 101384.0, "min": 96920.0, "max": 102956.0, "count": 20 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.794760242277, "min": 1200.4892579168904, "max": 1204.2571574161518, "count": 20 }, "SoccerTwos.Self-play.ELO.sum": { "value": 14409.537122907324, "min": 4814.783399651233, "max": 33639.309722443664, "count": 20 }, "SoccerTwos.Step.mean": { "value": 999776.0, "min": 49360.0, "max": 999776.0, "count": 20 }, "SoccerTwos.Step.sum": { "value": 999776.0, "min": 49360.0, "max": 999776.0, "count": 20 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0016028030076995492, "min": -0.004264697432518005, "max": 0.08232221752405167, "count": 20 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.08975696563720703, "min": -0.2430877536535263, "max": 4.857010841369629, "count": 20 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0017203426687046885, "min": -0.005274998489767313, "max": 0.08306208997964859, "count": 20 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.09633918851613998, "min": -0.3006749153137207, "max": 4.900663375854492, "count": 20 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 20 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 20 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11030000022479466, "min": -0.12444178960216579, "max": 0.052999999236177514, "count": 20 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.176800012588501, "min": -8.337599903345108, "max": 2.861999958753586, "count": 20 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11030000022479466, "min": -0.12444178960216579, "max": 0.052999999236177514, "count": 20 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.176800012588501, "min": -8.337599903345108, "max": 2.861999958753586, "count": 20 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016466266225458336, "min": 0.015288337600468365, "max": 0.01968905675690621, "count": 20 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.049398798676375005, "min": 0.018511507396968746, "max": 0.05831768332718639, "count": 20 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0008875883443094306, "min": 0.00012735439536484705, "max": 0.0018866164041780088, "count": 20 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0026627650329282917, "min": 0.0002547087907296941, "max": 0.005659849212534027, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0008889668918709504, "min": 0.00012729530923465406, "max": 0.0019485034459891415, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002666900675612851, "min": 0.0002545906184693081, "max": 0.005845510337967425, "count": 20 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.3029764060733328e-05, "min": 1.3029764060733328e-05, "max": 0.0004852640029471997, "count": 20 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 3.908929218219998e-05, "min": 3.908929218219998e-05, "max": 0.001392970021406, "count": 20 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10260593333333333, "min": 0.10260593333333333, "max": 0.19705279999999997, "count": 20 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.3078178, "min": 0.19705279999999997, "max": 0.578594, "count": 20 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.00016609540666666662, "min": 0.00016609540666666662, "max": 0.00582346272, "count": 20 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0004982862199999999, "min": 0.0004982862199999999, "max": 0.016717780600000003, "count": 20 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676309823", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=/content/ml-agents/training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676312152" }, "total": 2329.668662306, "count": 1, "self": 0.377563771000041, "children": { "run_training.setup": { "total": 0.1968287849999797, "count": 1, "self": 0.1968287849999797 }, "TrainerController.start_learning": { "total": 2329.09426975, "count": 1, "self": 1.3139922649606888, "children": { "TrainerController._reset_env": { "total": 6.492277372000331, "count": 5, "self": 6.492277372000331 }, "TrainerController.advance": { "total": 2320.937627842038, "count": 65137, "self": 1.6417428820550413, "children": { "env_step": { "total": 1704.1357154320035, "count": 65137, "self": 1291.5167122129455, "children": { "SubprocessEnvManager._take_step": { "total": 411.75434580099125, "count": 65137, "self": 11.198707932950924, "children": { "TorchPolicy.evaluate": { "total": 400.5556378680403, "count": 129396, "self": 73.7570395059746, "children": { "TorchPolicy.sample_actions": { "total": 326.7985983620657, "count": 129396, "self": 326.7985983620657 } } } } }, "workers": { "total": 0.8646574180665993, "count": 65137, "self": 0.0, "children": { "worker_root": { "total": 2324.302779778049, "count": 65137, "is_parallel": true, "self": 1236.861539408057, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002927940000063245, "count": 2, "is_parallel": true, "self": 0.0008689640001193766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020589759999438684, "count": 8, "is_parallel": true, "self": 0.0020589759999438684 } } }, "UnityEnvironment.step": { "total": 0.03854192399990097, "count": 1, "is_parallel": true, "self": 0.0011098549998678209, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008918969999740511, "count": 1, "is_parallel": true, "self": 0.0008918969999740511 }, "communicator.exchange": { "total": 0.032974581999951624, "count": 1, "is_parallel": true, "self": 0.032974581999951624 }, "steps_from_proto": { "total": 0.003565590000107477, "count": 2, "is_parallel": true, "self": 0.0007971310000129961, "children": { "_process_rank_one_or_two_observation": { "total": 0.002768459000094481, "count": 8, "is_parallel": true, "self": 0.002768459000094481 } } } } } } }, "UnityEnvironment.step": { "total": 1087.4337666899917, "count": 65136, "is_parallel": true, "self": 64.38289495199456, "children": { "UnityEnvironment._generate_step_input": { "total": 50.44968356303423, "count": 65136, "is_parallel": true, "self": 50.44968356303423 }, "communicator.exchange": { "total": 763.7788883129964, "count": 65136, "is_parallel": true, "self": 763.7788883129964 }, "steps_from_proto": { "total": 208.82229986196648, "count": 130272, "is_parallel": true, "self": 42.197285519956154, "children": { "_process_rank_one_or_two_observation": { "total": 166.62501434201033, "count": 521088, "is_parallel": true, "self": 166.62501434201033 } } } } }, "steps_from_proto": { "total": 0.0074736800004302495, "count": 8, "is_parallel": true, "self": 0.001717889000019568, "children": { "_process_rank_one_or_two_observation": { "total": 0.005755791000410682, "count": 32, "is_parallel": true, "self": 0.005755791000410682 } } } } } } } } }, "trainer_advance": { "total": 615.1601695279796, "count": 65137, "self": 11.888566690920243, "children": { "process_trajectory": { "total": 151.08626794405905, "count": 65137, "self": 150.48433769205917, "children": { "RLTrainer._checkpoint": { "total": 0.6019302519998746, "count": 2, "self": 0.6019302519998746 } } }, "_update_policy": { "total": 452.18533489300034, "count": 46, "self": 269.0533900849837, "children": { "TorchPOCAOptimizer.update": { "total": 183.13194480801667, "count": 2320, "self": 183.13194480801667 } } } } } } }, "trainer_threads": { "total": 8.290003279398661e-07, "count": 1, "self": 8.290003279398661e-07 }, "TrainerController._save_models": { "total": 0.35037144200032344, "count": 1, "self": 0.003085347000251204, "children": { "RLTrainer._checkpoint": { "total": 0.34728609500007224, "count": 1, "self": 0.34728609500007224 } } } } } } }