{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.7909812927246094, "min": 2.7909812927246094, "max": 2.8735625743865967, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28797.34375, "min": 28797.34375, "max": 29428.154296875, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.2357654571533203, "min": 0.4367538094520569, "max": 1.2357654571533203, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 253.3319091796875, "min": 84.73023986816406, "max": 253.3319091796875, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06977930348959989, "min": 0.06887715078415105, "max": 0.06977930348959989, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.34889651744799943, "min": 0.2755086031366042, "max": 0.34889651744799943, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17623081335834428, "min": 0.10139811878074326, "max": 0.17623081335834428, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8811540667917215, "min": 0.40559247512297303, "max": 0.8811540667917215, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.509090909090909, "min": 3.0, "max": 5.509090909090909, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 303.0, "min": 132.0, "max": 303.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.509090909090909, "min": 3.0, "max": 5.509090909090909, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 303.0, "min": 132.0, "max": 303.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682273964", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682274019" }, "total": 54.578588362000005, "count": 1, "self": 0.6368006950000336, "children": { "run_training.setup": { "total": 0.11350136299995484, "count": 1, "self": 0.11350136299995484 }, "TrainerController.start_learning": { "total": 53.82828630400002, "count": 1, "self": 0.11207899099827046, "children": { "TrainerController._reset_env": { "total": 3.820666545999984, "count": 1, "self": 3.820666545999984 }, "TrainerController.advance": { "total": 49.636060193001754, "count": 1870, "self": 0.03294616600123845, "children": { "env_step": { "total": 49.603114027000515, "count": 1870, "self": 36.085335017007196, "children": { "SubprocessEnvManager._take_step": { "total": 13.48667389199943, "count": 1870, "self": 0.17863678699814045, "children": { "TorchPolicy.evaluate": { "total": 13.30803710500129, "count": 1870, "self": 13.30803710500129 } } }, "workers": { "total": 0.031105117993888598, "count": 1870, "self": 0.0, "children": { "worker_root": { "total": 53.453637332001335, "count": 1870, "is_parallel": true, "self": 26.2376790720009, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005686973000024409, "count": 1, "is_parallel": true, "self": 0.004124490000208425, "children": { "_process_rank_one_or_two_observation": { "total": 0.001562482999815984, "count": 10, "is_parallel": true, "self": 0.001562482999815984 } } }, "UnityEnvironment.step": { "total": 0.05930108500001552, "count": 1, "is_parallel": true, "self": 0.0005017209999778061, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003546930000766224, "count": 1, "is_parallel": true, "self": 0.0003546930000766224 }, "communicator.exchange": { "total": 0.05678221799996663, "count": 1, "is_parallel": true, "self": 0.05678221799996663 }, "steps_from_proto": { "total": 0.001662452999994457, "count": 1, "is_parallel": true, "self": 0.0003645320000487118, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012979209999457453, "count": 10, "is_parallel": true, "self": 0.0012979209999457453 } } } } } } }, "UnityEnvironment.step": { "total": 27.215958260000434, "count": 1869, "is_parallel": true, "self": 1.1160162700007277, "children": { "UnityEnvironment._generate_step_input": { "total": 0.6211964489993989, "count": 1869, "is_parallel": true, "self": 0.6211964489993989 }, "communicator.exchange": { "total": 21.754065528001206, "count": 1869, "is_parallel": true, "self": 21.754065528001206 }, "steps_from_proto": { "total": 3.7246800129991016, "count": 1869, "is_parallel": true, "self": 0.79468652698813, "children": { "_process_rank_one_or_two_observation": { "total": 2.9299934860109715, "count": 18690, "is_parallel": true, "self": 2.9299934860109715 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00032925599998634425, "count": 1, "self": 0.00032925599998634425, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 49.28462176099515, "count": 46701, "is_parallel": true, "self": 1.1896125180080617, "children": { "process_trajectory": { "total": 28.09185101298715, "count": 46701, "is_parallel": true, "self": 28.09185101298715 }, "_update_policy": { "total": 20.00315822999994, "count": 9, "is_parallel": true, "self": 7.159385768000448, "children": { "TorchPPOOptimizer.update": { "total": 12.843772461999492, "count": 456, "is_parallel": true, "self": 12.843772461999492 } } } } } } } } }, "TrainerController._save_models": { "total": 0.259151318000022, "count": 1, "self": 0.0011480100000653692, "children": { "RLTrainer._checkpoint": { "total": 0.25800330799995663, "count": 1, "self": 0.25800330799995663 } } } } } } }