{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4069044589996338, "min": 1.4068857431411743, "max": 1.4275846481323242, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71124.6484375, "min": 68195.140625, "max": 76791.140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 124.85894206549118, "min": 101.82857142857142, "max": 383.7692307692308, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49569.0, "min": 49008.0, "max": 50360.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999883.0, "min": 49410.0, "max": 1999883.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999883.0, "min": 49410.0, "max": 1999883.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.249305248260498, "min": 0.1954614520072937, "max": 2.3675925731658936, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 892.9741821289062, "min": 25.214527130126953, "max": 1136.9207763671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4157779710719205, "min": 1.9055093175681062, "max": 3.873927873748166, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1356.0638545155525, "min": 245.8107019662857, "max": 1815.1937422454357, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4157779710719205, "min": 1.9055093175681062, "max": 3.873927873748166, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1356.0638545155525, "min": 245.8107019662857, "max": 1815.1937422454357, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017046981463014768, "min": 0.013323310226405738, "max": 0.019843240665310683, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.034093962926029536, "min": 0.026646620452811475, "max": 0.059529721995932046, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.040054341591894624, "min": 0.02059850326428811, "max": 0.05757815713683764, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08010868318378925, "min": 0.04119700652857622, "max": 0.1620842594653368, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.659473446874997e-06, "min": 4.659473446874997e-06, "max": 0.0002953358265547249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.318946893749995e-06, "min": 9.318946893749995e-06, "max": 0.00084416116861295, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101553125, "min": 0.101553125, "max": 0.198445275, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20310625, "min": 0.20310625, "max": 0.58138705, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.750093749999998e-05, "min": 8.750093749999998e-05, "max": 0.0049224192225, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017500187499999996, "min": 0.00017500187499999996, "max": 0.014071213795000002, "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": "1671040470", "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": "1671042589" }, "total": 2118.846268215, "count": 1, "self": 0.3961439159998008, "children": { "run_training.setup": { "total": 0.10898450199999843, "count": 1, "self": 0.10898450199999843 }, "TrainerController.start_learning": { "total": 2118.341139797, "count": 1, "self": 3.7132133690256524, "children": { "TrainerController._reset_env": { "total": 10.750932855999963, "count": 1, "self": 10.750932855999963 }, "TrainerController.advance": { "total": 2103.7674065709743, "count": 230871, "self": 3.955879890991582, "children": { "env_step": { "total": 1651.5048245489595, "count": 230871, "self": 1387.569882818836, "children": { "SubprocessEnvManager._take_step": { "total": 261.44128715097895, "count": 230871, "self": 14.03002230505092, "children": { "TorchPolicy.evaluate": { "total": 247.41126484592803, "count": 223076, "self": 62.98141403193813, "children": { "TorchPolicy.sample_actions": { "total": 184.4298508139899, "count": 223076, "self": 184.4298508139899 } } } } }, "workers": { "total": 2.493654579144504, "count": 230871, "self": 0.0, "children": { "worker_root": { "total": 2110.9258052539635, "count": 230871, "is_parallel": true, "self": 970.1732031530009, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002219518999936554, "count": 1, "is_parallel": true, "self": 0.00030169999990903307, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019178190000275208, "count": 2, "is_parallel": true, "self": 0.0019178190000275208 } } }, "UnityEnvironment.step": { "total": 0.026242776000003687, "count": 1, "is_parallel": true, "self": 0.00026940499992633704, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017662300001575204, "count": 1, "is_parallel": true, "self": 0.00017662300001575204 }, "communicator.exchange": { "total": 0.02511145599999054, "count": 1, "is_parallel": true, "self": 0.02511145599999054 }, "steps_from_proto": { "total": 0.0006852920000710583, "count": 1, "is_parallel": true, "self": 0.00023629800000435353, "children": { "_process_rank_one_or_two_observation": { "total": 0.00044899400006670476, "count": 2, "is_parallel": true, "self": 0.00044899400006670476 } } } } } } }, "UnityEnvironment.step": { "total": 1140.7526021009626, "count": 230870, "is_parallel": true, "self": 33.64231001404664, "children": { "UnityEnvironment._generate_step_input": { "total": 73.54028974794596, "count": 230870, "is_parallel": true, "self": 73.54028974794596 }, "communicator.exchange": { "total": 944.7908277429561, "count": 230870, "is_parallel": true, "self": 944.7908277429561 }, "steps_from_proto": { "total": 88.77917459601383, "count": 230870, "is_parallel": true, "self": 36.35431920904807, "children": { "_process_rank_one_or_two_observation": { "total": 52.42485538696576, "count": 461740, "is_parallel": true, "self": 52.42485538696576 } } } } } } } } } } }, "trainer_advance": { "total": 448.30670213102314, "count": 230871, "self": 5.791108351092703, "children": { "process_trajectory": { "total": 135.47881254192987, "count": 230871, "self": 135.01342358092973, "children": { "RLTrainer._checkpoint": { "total": 0.46538896100014426, "count": 4, "self": 0.46538896100014426 } } }, "_update_policy": { "total": 307.0367812380006, "count": 96, "self": 254.65593857099725, "children": { "TorchPPOOptimizer.update": { "total": 52.38084266700332, "count": 2880, "self": 52.38084266700332 } } } } } } }, "trainer_threads": { "total": 8.639999578008428e-07, "count": 1, "self": 8.639999578008428e-07 }, "TrainerController._save_models": { "total": 0.10958613699995112, "count": 1, "self": 0.002607602999887604, "children": { "RLTrainer._checkpoint": { "total": 0.10697853400006352, "count": 1, "self": 0.10697853400006352 } } } } } } }