{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.798236608505249, "min": 2.798236608505249, "max": 2.8822124004364014, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28841.42578125, "min": 28841.42578125, "max": 29548.44140625, "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": 1.2430400848388672, "min": 0.32107412815093994, "max": 1.2430400848388672, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 254.82321166992188, "min": 62.28838348388672, "max": 254.82321166992188, "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": 0.07022568537652785, "min": 0.06930703800741653, "max": 0.07022568537652785, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35112842688263923, "min": 0.2772281520296661, "max": 0.35112842688263923, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19644672958289874, "min": 0.12513568487438353, "max": 0.19644672958289874, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9822336479144937, "min": 0.5005427394975341, "max": 0.9822336479144937, "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": 5.654545454545454, "min": 3.3181818181818183, "max": 5.654545454545454, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 311.0, "min": 146.0, "max": 311.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.654545454545454, "min": 3.3181818181818183, "max": 5.654545454545454, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 311.0, "min": 146.0, "max": 311.0, "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": "1697458589", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697458647" }, "total": 57.78171331499999, "count": 1, "self": 0.4249648429999979, "children": { "run_training.setup": { "total": 0.047756512000006524, "count": 1, "self": 0.047756512000006524 }, "TrainerController.start_learning": { "total": 57.308991959999986, "count": 1, "self": 0.08190360699995836, "children": { "TrainerController._reset_env": { "total": 7.390591429000011, "count": 1, "self": 7.390591429000011 }, "TrainerController.advance": { "total": 49.67596463900003, "count": 1870, "self": 0.027941184999974666, "children": { "env_step": { "total": 49.648023454000054, "count": 1870, "self": 32.26725132100029, "children": { "SubprocessEnvManager._take_step": { "total": 17.351730499000098, "count": 1870, "self": 0.14614867100016227, "children": { "TorchPolicy.evaluate": { "total": 17.205581827999936, "count": 1870, "self": 17.205581827999936 } } }, "workers": { "total": 0.029041633999668193, "count": 1870, "self": 0.0, "children": { "worker_root": { "total": 57.0284644729995, "count": 1870, "is_parallel": true, "self": 32.050742550999445, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005560645999992175, "count": 1, "is_parallel": true, "self": 0.00421941600004061, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013412299999515653, "count": 10, "is_parallel": true, "self": 0.0013412299999515653 } } }, "UnityEnvironment.step": { "total": 0.05174759300001597, "count": 1, "is_parallel": true, "self": 0.0006634350000069844, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004513719999863497, "count": 1, "is_parallel": true, "self": 0.0004513719999863497 }, "communicator.exchange": { "total": 0.048115752000001066, "count": 1, "is_parallel": true, "self": 0.048115752000001066 }, "steps_from_proto": { "total": 0.0025170340000215674, "count": 1, "is_parallel": true, "self": 0.000421263000049521, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020957709999720464, "count": 10, "is_parallel": true, "self": 0.0020957709999720464 } } } } } } }, "UnityEnvironment.step": { "total": 24.977721922000057, "count": 1869, "is_parallel": true, "self": 1.0812811040009649, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5501727059997847, "count": 1869, "is_parallel": true, "self": 0.5501727059997847 }, "communicator.exchange": { "total": 19.856053594999338, "count": 1869, "is_parallel": true, "self": 19.856053594999338 }, "steps_from_proto": { "total": 3.49021451699997, "count": 1869, "is_parallel": true, "self": 0.663634151003123, "children": { "_process_rank_one_or_two_observation": { "total": 2.826580365996847, "count": 18690, "is_parallel": true, "self": 2.826580365996847 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022892699999488286, "count": 1, "self": 0.00022892699999488286, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 49.235486326997204, "count": 63121, "is_parallel": true, "self": 1.1487074529947279, "children": { "process_trajectory": { "total": 29.201081123002467, "count": 63121, "is_parallel": true, "self": 29.201081123002467 }, "_update_policy": { "total": 18.88569775100001, "count": 9, "is_parallel": true, "self": 5.991044205999742, "children": { "TorchPPOOptimizer.update": { "total": 12.894653545000267, "count": 456, "is_parallel": true, "self": 12.894653545000267 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16030335799999307, "count": 1, "self": 0.0007870469999886609, "children": { "RLTrainer._checkpoint": { "total": 0.1595163110000044, "count": 1, "self": 0.1595163110000044 } } } } } } }