{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0098216533660889, "min": 1.0098216533660889, "max": 2.871098041534424, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9641.77734375, "min": 9641.77734375, "max": 29434.49609375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.64568042755127, "min": 0.21739135682582855, "max": 12.64568042755127, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2465.90771484375, "min": 42.17392349243164, "max": 2542.72314453125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07000208617882533, "min": 0.06314282870288497, "max": 0.07739023068011282, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28000834471530134, "min": 0.2525713148115399, "max": 0.3869511534005641, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23218918299558114, "min": 0.10119927394792766, "max": 0.2912168715368299, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9287567319823246, "min": 0.40479709579171064, "max": 1.3746978114633, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.0, "min": 3.1363636363636362, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 138.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.1363636363636362, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 138.0, "max": 1378.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687739258", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687739741" }, "total": 483.39752663900003, "count": 1, "self": 0.5419846580001604, "children": { "run_training.setup": { "total": 0.0459174149999626, "count": 1, "self": 0.0459174149999626 }, "TrainerController.start_learning": { "total": 482.8096245659999, "count": 1, "self": 0.5475428449938136, "children": { "TrainerController._reset_env": { "total": 4.539977157999942, "count": 1, "self": 4.539977157999942 }, "TrainerController.advance": { "total": 477.5693729100061, "count": 18201, "self": 0.28011108602584045, "children": { "env_step": { "total": 477.28926182398027, "count": 18201, "self": 348.77115501098547, "children": { "SubprocessEnvManager._take_step": { "total": 128.24141572999758, "count": 18201, "self": 1.864118452996081, "children": { "TorchPolicy.evaluate": { "total": 126.3772972770015, "count": 18201, "self": 126.3772972770015 } } }, "workers": { "total": 0.27669108299721756, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 481.1767888360082, "count": 18201, "is_parallel": true, "self": 224.7081132120179, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005813375999991877, "count": 1, "is_parallel": true, "self": 0.0042666480001116724, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015467279998802042, "count": 10, "is_parallel": true, "self": 0.0015467279998802042 } } }, "UnityEnvironment.step": { "total": 0.11012607199995728, "count": 1, "is_parallel": true, "self": 0.0006622970000762507, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043085499999051535, "count": 1, "is_parallel": true, "self": 0.00043085499999051535 }, "communicator.exchange": { "total": 0.10672583699999905, "count": 1, "is_parallel": true, "self": 0.10672583699999905 }, "steps_from_proto": { "total": 0.0023070829998914633, "count": 1, "is_parallel": true, "self": 0.00041026599978977174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018968170001016915, "count": 10, "is_parallel": true, "self": 0.0018968170001016915 } } } } } } }, "UnityEnvironment.step": { "total": 256.4686756239903, "count": 18200, "is_parallel": true, "self": 10.792960972987316, "children": { "UnityEnvironment._generate_step_input": { "total": 5.463032680991546, "count": 18200, "is_parallel": true, "self": 5.463032680991546 }, "communicator.exchange": { "total": 204.46761137600674, "count": 18200, "is_parallel": true, "self": 204.46761137600674 }, "steps_from_proto": { "total": 35.74507059400469, "count": 18200, "is_parallel": true, "self": 6.492281819993423, "children": { "_process_rank_one_or_two_observation": { "total": 29.252788774011265, "count": 182000, "is_parallel": true, "self": 29.252788774011265 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013865300002180447, "count": 1, "self": 0.00013865300002180447, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 473.9300563400059, "count": 449839, "is_parallel": true, "self": 9.976517353993813, "children": { "process_trajectory": { "total": 258.9866650880123, "count": 449839, "is_parallel": true, "self": 257.8226263920121, "children": { "RLTrainer._checkpoint": { "total": 1.1640386960001479, "count": 4, "is_parallel": true, "self": 1.1640386960001479 } } }, "_update_policy": { "total": 204.9668738979998, "count": 90, "is_parallel": true, "self": 78.98457187399697, "children": { "TorchPPOOptimizer.update": { "total": 125.98230202400282, "count": 4587, "is_parallel": true, "self": 125.98230202400282 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1525930000000244, "count": 1, "self": 0.0009839860001648049, "children": { "RLTrainer._checkpoint": { "total": 0.1516090139998596, "count": 1, "self": 0.1516090139998596 } } } } } } }