{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.399404525756836, "min": 1.3993847370147705, "max": 1.4282042980194092, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69472.0390625, "min": 69042.4921875, "max": 77480.5, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 115.24883720930232, "min": 108.91629955947137, "max": 390.1796875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49557.0, "min": 49063.0, "max": 50201.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999960.0, "min": 49348.0, "max": 1999960.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999960.0, "min": 49348.0, "max": 1999960.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3263306617736816, "min": 0.06068781390786171, "max": 2.3524115085601807, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1000.3221435546875, "min": 7.707352161407471, "max": 1026.75, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5133702425069586, "min": 1.7918434236931988, "max": 3.8198634717675994, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1510.7492042779922, "min": 227.56411480903625, "max": 1656.2133178710938, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5133702425069586, "min": 1.7918434236931988, "max": 3.8198634717675994, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1510.7492042779922, "min": 227.56411480903625, "max": 1656.2133178710938, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.022108360500230143, "min": 0.012974449577288598, "max": 0.022108360500230143, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.044216721000460285, "min": 0.02694974663160489, "max": 0.05873404970237364, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04657639600336552, "min": 0.022803141083568335, "max": 0.06670776593188446, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09315279200673104, "min": 0.04560628216713667, "max": 0.18257888903220496, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.209398596900003e-06, "min": 4.209398596900003e-06, "max": 0.0002953602765465749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.418797193800007e-06, "min": 8.418797193800007e-06, "max": 0.0008441305686231499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1014031, "min": 0.1014031, "max": 0.19845342500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2028062, "min": 0.2028062, "max": 0.5813768500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.001469000000007e-05, "min": 8.001469000000007e-05, "max": 0.0049228259075, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016002938000000014, "min": 0.00016002938000000014, "max": 0.014070704815000003, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1670792067", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1670794255" }, "total": 2187.3471971789995, "count": 1, "self": 0.3964854979994925, "children": { "run_training.setup": { "total": 0.4299121259999765, "count": 1, "self": 0.4299121259999765 }, "TrainerController.start_learning": { "total": 2186.520799555, "count": 1, "self": 3.6737442039634516, "children": { "TrainerController._reset_env": { "total": 10.508478303000004, "count": 1, "self": 10.508478303000004 }, "TrainerController.advance": { "total": 2172.212664476036, "count": 230393, "self": 4.096621761004826, "children": { "env_step": { "total": 1711.7142273600512, "count": 230393, "self": 1434.5033309911562, "children": { "SubprocessEnvManager._take_step": { "total": 274.7132061359767, "count": 230393, "self": 14.024938907065405, "children": { "TorchPolicy.evaluate": { "total": 260.6882672289113, "count": 222944, "self": 64.55022383489421, "children": { "TorchPolicy.sample_actions": { "total": 196.13804339401707, "count": 222944, "self": 196.13804339401707 } } } } }, "workers": { "total": 2.4976902329183304, "count": 230393, "self": 0.0, "children": { "worker_root": { "total": 2179.2498037379282, "count": 230393, "is_parallel": true, "self": 998.127821664853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021103959999777544, "count": 1, "is_parallel": true, "self": 0.00029359100000192484, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018168049999758296, "count": 2, "is_parallel": true, "self": 0.0018168049999758296 } } }, "UnityEnvironment.step": { "total": 0.027209695999999894, "count": 1, "is_parallel": true, "self": 0.0002683650000108173, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001746730000036223, "count": 1, "is_parallel": true, "self": 0.0001746730000036223 }, "communicator.exchange": { "total": 0.026069340999981705, "count": 1, "is_parallel": true, "self": 0.026069340999981705 }, "steps_from_proto": { "total": 0.0006973170000037499, "count": 1, "is_parallel": true, "self": 0.0002398390000166728, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045747799998707706, "count": 2, "is_parallel": true, "self": 0.00045747799998707706 } } } } } } }, "UnityEnvironment.step": { "total": 1181.1219820730753, "count": 230392, "is_parallel": true, "self": 34.36778842209674, "children": { "UnityEnvironment._generate_step_input": { "total": 75.05278143598036, "count": 230392, "is_parallel": true, "self": 75.05278143598036 }, "communicator.exchange": { "total": 980.7481968400073, "count": 230392, "is_parallel": true, "self": 980.7481968400073 }, "steps_from_proto": { "total": 90.9532153749908, "count": 230392, "is_parallel": true, "self": 37.19664421291969, "children": { "_process_rank_one_or_two_observation": { "total": 53.75657116207111, "count": 460784, "is_parallel": true, "self": 53.75657116207111 } } } } } } } } } } }, "trainer_advance": { "total": 456.40181535498016, "count": 230393, "self": 5.860637586947917, "children": { "process_trajectory": { "total": 137.36401602203188, "count": 230393, "self": 136.88624085603186, "children": { "RLTrainer._checkpoint": { "total": 0.4777751660000149, "count": 4, "self": 0.4777751660000149 } } }, "_update_policy": { "total": 313.17716174600037, "count": 96, "self": 260.18686717800034, "children": { "TorchPPOOptimizer.update": { "total": 52.990294568000024, "count": 2880, "self": 52.990294568000024 } } } } } } }, "trainer_threads": { "total": 9.960003808373585e-07, "count": 1, "self": 9.960003808373585e-07 }, "TrainerController._save_models": { "total": 0.12591157599990765, "count": 1, "self": 0.0021731349997935467, "children": { "RLTrainer._checkpoint": { "total": 0.12373844100011411, "count": 1, "self": 0.12373844100011411 } } } } } } }