{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7088449001312256, "min": 1.6656020879745483, "max": 3.295809745788574, "count": 2118 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30895.916015625, "min": 17193.107421875, "max": 105465.9140625, "count": 2118 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 127.8974358974359, "min": 53.077777777777776, "max": 999.0, "count": 2118 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19952.0, "min": 9316.0, "max": 31056.0, "count": 2118 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1393.2070667626276, "min": 1194.0179170001877, "max": 1494.8070027585331, "count": 2113 }, "SoccerTwos.Self-play.ELO.sum": { "value": 108670.15120748496, "min": 2391.7424111429464, "max": 268500.25612255756, "count": 2113 }, "SoccerTwos.Step.mean": { "value": 21199822.0, "min": 19812.0, "max": 21199822.0, "count": 2119 }, "SoccerTwos.Step.sum": { "value": 21199822.0, "min": 19812.0, "max": 21199822.0, "count": 2119 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.11808216571807861, "min": -0.15146400034427643, "max": 0.13950079679489136, "count": 2119 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.3284912109375, "min": -21.204959869384766, "max": 16.012798309326172, "count": 2119 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.12490028887987137, "min": -0.15625835955142975, "max": 0.14536117017269135, "count": 2119 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.867122650146484, "min": -21.876171112060547, "max": 16.468259811401367, "count": 2119 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2119 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2119 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.16714936570276187, "min": -0.6353999997178713, "max": 0.4474086916964987, "count": 2119 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.204799890518188, "min": -59.412600100040436, "max": 46.18160021305084, "count": 2119 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16714936570276187, "min": -0.6353999997178713, "max": 0.4474086916964987, "count": 2119 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.204799890518188, "min": -59.412600100040436, "max": 46.18160021305084, "count": 2119 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2119 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2119 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.041809182005818, "min": 0.01977048081521172, "max": 0.044036700596188895, "count": 1024 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.041809182005818, "min": 0.01977048081521172, "max": 0.044036700596188895, "count": 1024 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07537970733828843, "min": 0.0017333200696157292, "max": 0.11558356927707791, "count": 1024 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07537970733828843, "min": 0.0017333200696157292, "max": 0.11558356927707791, "count": 1024 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08129970403388143, "min": 0.0018409219002933242, "max": 0.1513616295531392, "count": 1024 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08129970403388143, "min": 0.0018409219002933242, "max": 0.1513616295531392, "count": 1024 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.00030000000000000003, "count": 1024 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.00030000000000000003, "count": 1024 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999998, "min": 0.19999999999999996, "max": 0.19999999999999998, "count": 1024 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999998, "min": 0.19999999999999996, "max": 0.19999999999999998, "count": 1024 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.005, "count": 1024 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.005, "count": 1024 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714101219", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/ubuntu20/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714173699" }, "total": 72479.418903871, "count": 1, "self": 10.004975321993697, "children": { "run_training.setup": { "total": 0.00968369700058247, "count": 1, "self": 0.00968369700058247 }, "TrainerController.start_learning": { "total": 72469.404244852, "count": 1, "self": 21.888783656962914, "children": { "TrainerController._reset_env": { "total": 2.9812066590493487, "count": 106, "self": 2.9812066590493487 }, "TrainerController.advance": { "total": 72444.219184276, "count": 1429364, "self": 23.230157327707275, "children": { "env_step": { "total": 58573.05581548553, "count": 1429364, "self": 18015.47316901359, "children": { "SubprocessEnvManager._take_step": { "total": 40542.46051155147, "count": 1429364, "self": 183.41604163614102, "children": { "TorchPolicy.evaluate": { "total": 40359.04446991533, "count": 2665775, "self": 40359.04446991533 } } }, "workers": { "total": 15.122134920475219, "count": 1429363, "self": 0.0, "children": { "worker_root": { "total": 72423.0840364866, "count": 1429363, "is_parallel": true, "self": 56851.92234566223, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019098580014542677, "count": 2, "is_parallel": true, "self": 0.0005025739919801708, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014072840094740968, "count": 8, "is_parallel": true, "self": 0.0014072840094740968 } } }, "UnityEnvironment.step": { "total": 0.022356173998559825, "count": 1, "is_parallel": true, "self": 0.0003792550014622975, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003022740020242054, "count": 1, "is_parallel": true, "self": 0.0003022740020242054 }, "communicator.exchange": { "total": 0.0205102519976208, "count": 1, "is_parallel": true, "self": 0.0205102519976208 }, "steps_from_proto": { "total": 0.0011643929974525236, "count": 2, "is_parallel": true, "self": 0.00025741099670995027, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009069820007425733, "count": 8, "is_parallel": true, "self": 0.0009069820007425733 } } } } } } }, "UnityEnvironment.step": { "total": 15571.059210241528, "count": 1429362, "is_parallel": true, "self": 483.5320281779568, "children": { "UnityEnvironment._generate_step_input": { "total": 312.8383523944467, "count": 1429362, "is_parallel": true, "self": 312.8383523944467 }, "communicator.exchange": { "total": 13387.107385548188, "count": 1429362, "is_parallel": true, "self": 13387.107385548188 }, "steps_from_proto": { "total": 1387.5814441209368, "count": 2858724, "is_parallel": true, "self": 290.3145172816985, "children": { "_process_rank_one_or_two_observation": { "total": 1097.2669268392383, "count": 11434896, "is_parallel": true, "self": 1097.2669268392383 } } } } }, "steps_from_proto": { "total": 0.102480582849239, "count": 210, "is_parallel": true, "self": 0.021618372837110655, "children": { "_process_rank_one_or_two_observation": { "total": 0.08086221001212834, "count": 840, "is_parallel": true, "self": 0.08086221001212834 } } } } } } } } }, "trainer_advance": { "total": 13847.933211462761, "count": 1429363, "self": 170.83017437849048, "children": { "process_trajectory": { "total": 8711.664205260236, "count": 1429363, "self": 8698.837213972212, "children": { "RLTrainer._checkpoint": { "total": 12.826991288024146, "count": 42, "self": 12.826991288024146 } } }, "_update_policy": { "total": 4965.438831824034, "count": 1025, "self": 1810.928020163461, "children": { "TorchPOCAOptimizer.update": { "total": 3154.5108116605734, "count": 82064, "self": 3154.5108116605734 } } } } } } }, "trainer_threads": { "total": 6.579939508810639e-07, "count": 1, "self": 6.579939508810639e-07 }, "TrainerController._save_models": { "total": 0.3150696020020405, "count": 1, "self": 0.021174097011680715, "children": { "RLTrainer._checkpoint": { "total": 0.29389550499035977, "count": 1, "self": 0.29389550499035977 } } } } } } }