{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050724506378174, "min": 1.4050724506378174, "max": 1.4260363578796387, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71348.171875, "min": 67131.1875, "max": 78393.546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.37142857142857, "min": 80.3040650406504, "max": 423.7647058823529, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49488.0, "min": 49130.0, "max": 50428.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999978.0, "min": 49797.0, "max": 1999978.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999978.0, "min": 49797.0, "max": 1999978.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4774155616760254, "min": 0.19923412799835205, "max": 2.4966280460357666, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1387.3526611328125, "min": 23.509626388549805, "max": 1528.638427734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.821461963972875, "min": 1.9418142019944675, "max": 4.01961160337925, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2140.01869982481, "min": 229.13407583534718, "max": 2411.3285405635834, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.821461963972875, "min": 1.9418142019944675, "max": 4.01961160337925, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2140.01869982481, "min": 229.13407583534718, "max": 2411.3285405635834, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016913121550330996, "min": 0.014056400531424313, "max": 0.02067926305171568, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050739364650992984, "min": 0.028230936994077638, "max": 0.06203778915514704, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04915729094710614, "min": 0.020418365796407066, "max": 0.06181498946001132, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14747187284131844, "min": 0.04083673159281413, "max": 0.1765836046387752, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.045648651483343e-06, "min": 4.045648651483343e-06, "max": 0.00029535330154889993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2136945954450027e-05, "min": 1.2136945954450027e-05, "max": 0.0008443164185611999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10134851666666672, "min": 0.10134851666666672, "max": 0.1984511, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30404555000000016, "min": 0.20784454999999996, "max": 0.5814388, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.729098166666682e-05, "min": 7.729098166666682e-05, "max": 0.00492270989, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00023187294500000044, "min": 0.00023187294500000044, "max": 0.014073796120000003, "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": "1670513353", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670515644" }, "total": 2291.0350670010002, "count": 1, "self": 0.39423939700009214, "children": { "run_training.setup": { "total": 0.11214533700001539, "count": 1, "self": 0.11214533700001539 }, "TrainerController.start_learning": { "total": 2290.528682267, "count": 1, "self": 3.999183039977197, "children": { "TrainerController._reset_env": { "total": 12.568585272000007, "count": 1, "self": 12.568585272000007 }, "TrainerController.advance": { "total": 2273.842163602023, "count": 232571, "self": 4.308466097973451, "children": { "env_step": { "total": 1777.5139391400207, "count": 232571, "self": 1494.7297845091275, "children": { "SubprocessEnvManager._take_step": { "total": 280.1051325469634, "count": 232571, "self": 14.582203834912889, "children": { "TorchPolicy.evaluate": { "total": 265.5229287120505, "count": 222970, "self": 66.5436936231086, "children": { "TorchPolicy.sample_actions": { "total": 198.9792350889419, "count": 222970, "self": 198.9792350889419 } } } } }, "workers": { "total": 2.6790220839297376, "count": 232571, "self": 0.0, "children": { "worker_root": { "total": 2282.4905394619527, "count": 232571, "is_parallel": true, "self": 1051.846836333977, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021987810000041463, "count": 1, "is_parallel": true, "self": 0.0003036200000678946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018951609999362518, "count": 2, "is_parallel": true, "self": 0.0018951609999362518 } } }, "UnityEnvironment.step": { "total": 0.04598960399999896, "count": 1, "is_parallel": true, "self": 0.0003172800000470488, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019336599996222503, "count": 1, "is_parallel": true, "self": 0.00019336599996222503 }, "communicator.exchange": { "total": 0.044687524999972084, "count": 1, "is_parallel": true, "self": 0.044687524999972084 }, "steps_from_proto": { "total": 0.0007914330000176051, "count": 1, "is_parallel": true, "self": 0.0002547480000316682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005366849999859369, "count": 2, "is_parallel": true, "self": 0.0005366849999859369 } } } } } } }, "UnityEnvironment.step": { "total": 1230.6437031279756, "count": 232570, "is_parallel": true, "self": 35.60049713196963, "children": { "UnityEnvironment._generate_step_input": { "total": 75.26869277997775, "count": 232570, "is_parallel": true, "self": 75.26869277997775 }, "communicator.exchange": { "total": 1025.2778160910555, "count": 232570, "is_parallel": true, "self": 1025.2778160910555 }, "steps_from_proto": { "total": 94.4966971249728, "count": 232570, "is_parallel": true, "self": 38.93901246394125, "children": { "_process_rank_one_or_two_observation": { "total": 55.557684661031544, "count": 465140, "is_parallel": true, "self": 55.557684661031544 } } } } } } } } } } }, "trainer_advance": { "total": 492.01975836402886, "count": 232571, "self": 6.104431782014046, "children": { "process_trajectory": { "total": 153.77021198101437, "count": 232571, "self": 153.29498102701467, "children": { "RLTrainer._checkpoint": { "total": 0.4752309539996986, "count": 4, "self": 0.4752309539996986 } } }, "_update_policy": { "total": 332.14511460100044, "count": 97, "self": 276.96564762999736, "children": { "TorchPPOOptimizer.update": { "total": 55.17946697100308, "count": 2910, "self": 55.17946697100308 } } } } } } }, "trainer_threads": { "total": 1.0320000001229346e-06, "count": 1, "self": 1.0320000001229346e-06 }, "TrainerController._save_models": { "total": 0.11874932099999569, "count": 1, "self": 0.0020628289998967375, "children": { "RLTrainer._checkpoint": { "total": 0.11668649200009895, "count": 1, "self": 0.11668649200009895 } } } } } } }