{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6146581768989563, "min": 0.4877191185951233, "max": 2.8522908687591553, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6301.4755859375, "min": 4384.46875, "max": 29653.296875, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.084091186523438, "min": 0.37808966636657715, "max": 14.18260383605957, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1380.240966796875, "min": 36.67469787597656, "max": 1453.4964599609375, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.711111111111112, "min": 3.522727272727273, "max": 27.884615384615383, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1247.0, "min": 155.0, "max": 1521.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.711111111111112, "min": 3.522727272727273, "max": 27.884615384615383, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1247.0, "min": 155.0, "max": 1521.0, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07095538789187283, "min": 0.06114683207261431, "max": 0.07731391892622352, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35477693945936417, "min": 0.2449065320953891, "max": 0.3865695946311176, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15892484836718615, "min": 0.13363706204565423, "max": 0.28440946625436053, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7946242418359307, "min": 0.5345482481826169, "max": 1.3627852429361904, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6800994400000014e-06, "min": 1.6800994400000014e-06, "max": 0.00029835000055, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.400497200000007e-06, "min": 8.400497200000007e-06, "max": 0.0014769000076999999, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10056000000000001, "min": 0.10056000000000001, "max": 0.19945000000000002, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5028, "min": 0.4062, "max": 0.9923000000000001, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.794400000000003e-05, "min": 3.794400000000003e-05, "max": 0.004972555, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00018972000000000016, "min": 0.00018972000000000016, "max": 0.02461577, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710687100", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710689300" }, "total": 2199.3389862429995, "count": 1, "self": 0.4343201570000019, "children": { "run_training.setup": { "total": 0.09340444699955697, "count": 1, "self": 0.09340444699955697 }, "TrainerController.start_learning": { "total": 2198.811261639, "count": 1, "self": 2.792321032158725, "children": { "TrainerController._reset_env": { "total": 2.0872996520001834, "count": 1, "self": 2.0872996520001834 }, "TrainerController.advance": { "total": 2193.8337521108406, "count": 90940, "self": 1.4391148969034475, "children": { "env_step": { "total": 2192.394637213937, "count": 90940, "self": 1371.5250379679637, "children": { "SubprocessEnvManager._take_step": { "total": 819.2216098889267, "count": 90940, "self": 7.535240109797087, "children": { "TorchPolicy.evaluate": { "total": 811.6863697791296, "count": 90940, "self": 811.6863697791296 } } }, "workers": { "total": 1.6479893570467539, "count": 90940, "self": 0.0, "children": { "worker_root": { "total": 2193.03557291, "count": 90940, "is_parallel": true, "self": 1051.0183055737534, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002191622000282223, "count": 1, "is_parallel": true, "self": 0.0006575389988938696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015340830013883533, "count": 10, "is_parallel": true, "self": 0.0015340830013883533 } } }, "UnityEnvironment.step": { "total": 0.03989202299999306, "count": 1, "is_parallel": true, "self": 0.0008064760004344862, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004623770000762306, "count": 1, "is_parallel": true, "self": 0.0004623770000762306 }, "communicator.exchange": { "total": 0.03618441399976291, "count": 1, "is_parallel": true, "self": 0.03618441399976291 }, "steps_from_proto": { "total": 0.002438755999719433, "count": 1, "is_parallel": true, "self": 0.00046011699851078447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019786390012086486, "count": 10, "is_parallel": true, "self": 0.0019786390012086486 } } } } } } }, "UnityEnvironment.step": { "total": 1142.0172673362467, "count": 90939, "is_parallel": true, "self": 51.632565194197014, "children": { "UnityEnvironment._generate_step_input": { "total": 27.765041421186652, "count": 90939, "is_parallel": true, "self": 27.765041421186652 }, "communicator.exchange": { "total": 888.4825358559583, "count": 90939, "is_parallel": true, "self": 888.4825358559583 }, "steps_from_proto": { "total": 174.13712486490476, "count": 90939, "is_parallel": true, "self": 33.27397351507261, "children": { "_process_rank_one_or_two_observation": { "total": 140.86315134983215, "count": 909390, "is_parallel": true, "self": 140.86315134983215 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002993830003106268, "count": 1, "self": 0.0002993830003106268, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2171.239855954347, "count": 2684027, "is_parallel": true, "self": 61.29481332234809, "children": { "process_trajectory": { "total": 992.4873533459922, "count": 2684027, "is_parallel": true, "self": 989.7876090849923, "children": { "RLTrainer._checkpoint": { "total": 2.699744260999978, "count": 20, "is_parallel": true, "self": 2.699744260999978 } } }, "_update_policy": { "total": 1117.4576892860068, "count": 454, "is_parallel": true, "self": 277.859193023015, "children": { "TorchPPOOptimizer.update": { "total": 839.5984962629918, "count": 23139, "is_parallel": true, "self": 839.5984962629918 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0975894610000978, "count": 1, "self": 0.0013217030000305385, "children": { "RLTrainer._checkpoint": { "total": 0.09626775800006726, "count": 1, "self": 0.09626775800006726 } } } } } } }