{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4076530933380127, "min": 1.4076530933380127, "max": 1.4283275604248047, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70054.671875, "min": 68346.5234375, "max": 76451.8046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 105.78833693304536, "min": 98.4820717131474, "max": 416.0833333333333, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48980.0, "min": 48953.0, "max": 50173.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999981.0, "min": 49397.0, "max": 1999981.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999981.0, "min": 49397.0, "max": 1999981.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2543015480041504, "min": -0.043683215975761414, "max": 2.353395462036133, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1043.7415771484375, "min": -5.198302745819092, "max": 1138.61767578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5007018219060053, "min": 1.8603073175714797, "max": 3.8366796333085067, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1620.8249435424805, "min": 221.3765707910061, "max": 1830.0961850881577, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5007018219060053, "min": 1.8603073175714797, "max": 3.8366796333085067, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1620.8249435424805, "min": 221.3765707910061, "max": 1830.0961850881577, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01880734783868926, "min": 0.01301764731680224, "max": 0.020109623441627873, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05642204351606778, "min": 0.028850955479235076, "max": 0.05714742003425878, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0529785597903861, "min": 0.021720631637920935, "max": 0.0529785597903861, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1589356793711583, "min": 0.04344126327584187, "max": 0.1589356793711583, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1166489611499964e-06, "min": 3.1166489611499964e-06, "max": 0.0002952949515683499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.34994688344999e-06, "min": 9.34994688344999e-06, "max": 0.000843714018762, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10103885, "min": 0.10103885, "max": 0.19843164999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30311655, "min": 0.20721500000000004, "max": 0.581238, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.183861499999995e-05, "min": 6.183861499999995e-05, "max": 0.004921739335, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018551584499999985, "min": 0.00018551584499999985, "max": 0.014063776200000003, "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": "1671110597", "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": "1671112906" }, "total": 2309.931540391, "count": 1, "self": 0.4394172120005351, "children": { "run_training.setup": { "total": 0.11859524699980284, "count": 1, "self": 0.11859524699980284 }, "TrainerController.start_learning": { "total": 2309.373527932, "count": 1, "self": 3.907819113037476, "children": { "TrainerController._reset_env": { "total": 10.735837357000037, "count": 1, "self": 10.735837357000037 }, "TrainerController.advance": { "total": 2294.608417792963, "count": 230862, "self": 4.110854932147049, "children": { "env_step": { "total": 1811.300789510949, "count": 230862, "self": 1525.5044853450718, "children": { "SubprocessEnvManager._take_step": { "total": 283.1477390989155, "count": 230862, "self": 14.803389808928614, "children": { "TorchPolicy.evaluate": { "total": 268.3443492899869, "count": 222905, "self": 67.3323117460252, "children": { "TorchPolicy.sample_actions": { "total": 201.0120375439617, "count": 222905, "self": 201.0120375439617 } } } } }, "workers": { "total": 2.648565066961737, "count": 230862, "self": 0.0, "children": { "worker_root": { "total": 2301.465923960015, "count": 230862, "is_parallel": true, "self": 1039.9994047848807, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002123191000009683, "count": 1, "is_parallel": true, "self": 0.0003265070001816639, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017966839998280193, "count": 2, "is_parallel": true, "self": 0.0017966839998280193 } } }, "UnityEnvironment.step": { "total": 0.02815786900009698, "count": 1, "is_parallel": true, "self": 0.0002542640002047847, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018198099996880046, "count": 1, "is_parallel": true, "self": 0.00018198099996880046 }, "communicator.exchange": { "total": 0.027002865999975256, "count": 1, "is_parallel": true, "self": 0.027002865999975256 }, "steps_from_proto": { "total": 0.0007187579999481386, "count": 1, "is_parallel": true, "self": 0.00023035100002744002, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004884069999206986, "count": 2, "is_parallel": true, "self": 0.0004884069999206986 } } } } } } }, "UnityEnvironment.step": { "total": 1261.4665191751344, "count": 230861, "is_parallel": true, "self": 36.2371347401122, "children": { "UnityEnvironment._generate_step_input": { "total": 80.23490385896685, "count": 230861, "is_parallel": true, "self": 80.23490385896685 }, "communicator.exchange": { "total": 1048.1142477200174, "count": 230861, "is_parallel": true, "self": 1048.1142477200174 }, "steps_from_proto": { "total": 96.88023285603799, "count": 230861, "is_parallel": true, "self": 39.866932276291436, "children": { "_process_rank_one_or_two_observation": { "total": 57.013300579746556, "count": 461722, "is_parallel": true, "self": 57.013300579746556 } } } } } } } } } } }, "trainer_advance": { "total": 479.1967733498668, "count": 230862, "self": 5.935917099808648, "children": { "process_trajectory": { "total": 146.84192475305986, "count": 230862, "self": 145.58572854906015, "children": { "RLTrainer._checkpoint": { "total": 1.256196203999707, "count": 10, "self": 1.256196203999707 } } }, "_update_policy": { "total": 326.4189314969983, "count": 97, "self": 272.23172464500635, "children": { "TorchPPOOptimizer.update": { "total": 54.18720685199196, "count": 2910, "self": 54.18720685199196 } } } } } } }, "trainer_threads": { "total": 1.1159995665366296e-06, "count": 1, "self": 1.1159995665366296e-06 }, "TrainerController._save_models": { "total": 0.12145255299992641, "count": 1, "self": 0.0021054699996057025, "children": { "RLTrainer._checkpoint": { "total": 0.11934708300032071, "count": 1, "self": 0.11934708300032071 } } } } } } }