{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4076613187789917, "min": 1.4076613187789917, "max": 1.4292466640472412, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70471.75, "min": 68583.265625, "max": 76732.4296875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.16042780748663, "min": 84.55440414507773, "max": 425.364406779661, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49458.0, "min": 48870.0, "max": 50193.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999978.0, "min": 49561.0, "max": 1999978.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999978.0, "min": 49561.0, "max": 1999978.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3862392902374268, "min": 0.02317376807332039, "max": 2.426459789276123, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1338.6802978515625, "min": 2.7113308906555176, "max": 1340.10009765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7184821130332675, "min": 1.6339416154938886, "max": 3.926547460258007, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2086.068465411663, "min": 191.17116901278496, "max": 2136.041818380356, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7184821130332675, "min": 1.6339416154938886, "max": 3.926547460258007, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2086.068465411663, "min": 191.17116901278496, "max": 2136.041818380356, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015324211076302973, "min": 0.013046631370121353, "max": 0.019113207572566654, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04597263322890892, "min": 0.029896785869156395, "max": 0.05662114246903609, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05521743661827511, "min": 0.022361741277078788, "max": 0.05733851169546445, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16565230985482535, "min": 0.044723482554157576, "max": 0.16565230985482535, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1754989415333286e-06, "min": 3.1754989415333286e-06, "max": 0.00029527732657422495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.526496824599986e-06, "min": 9.526496824599986e-06, "max": 0.0008440143186619001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1010584666666667, "min": 0.1010584666666667, "max": 0.19842577500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031754000000001, "min": 0.20724710000000002, "max": 0.5813381, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.281748666666659e-05, "min": 6.281748666666659e-05, "max": 0.004921446172500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018845245999999977, "min": 0.00018845245999999977, "max": 0.014068771189999999, "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": "1721329254", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721331628" }, "total": 2373.571014137, "count": 1, "self": 0.4413373100001081, "children": { "run_training.setup": { "total": 0.05479096499999514, "count": 1, "self": 0.05479096499999514 }, "TrainerController.start_learning": { "total": 2373.074885862, "count": 1, "self": 4.119834652954978, "children": { "TrainerController._reset_env": { "total": 2.7238258650000375, "count": 1, "self": 2.7238258650000375 }, "TrainerController.advance": { "total": 2366.120215676045, "count": 231794, "self": 4.654412921293897, "children": { "env_step": { "total": 1874.4851584629616, "count": 231794, "self": 1548.121001054912, "children": { "SubprocessEnvManager._take_step": { "total": 323.59811903904557, "count": 231794, "self": 16.82772799615043, "children": { "TorchPolicy.evaluate": { "total": 306.77039104289514, "count": 222898, "self": 306.77039104289514 } } }, "workers": { "total": 2.7660383690039225, "count": 231794, "self": 0.0, "children": { "worker_root": { "total": 2366.1637213080116, "count": 231794, "is_parallel": true, "self": 1119.2865694670622, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009365939999952388, "count": 1, "is_parallel": true, "self": 0.000235838999913085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007007550000821539, "count": 2, "is_parallel": true, "self": 0.0007007550000821539 } } }, "UnityEnvironment.step": { "total": 0.03008587199997237, "count": 1, "is_parallel": true, "self": 0.0003662049999775263, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002053389999900901, "count": 1, "is_parallel": true, "self": 0.0002053389999900901 }, "communicator.exchange": { "total": 0.02876436100001456, "count": 1, "is_parallel": true, "self": 0.02876436100001456 }, "steps_from_proto": { "total": 0.0007499669999901926, "count": 1, "is_parallel": true, "self": 0.00018881499994449769, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005611520000456949, "count": 2, "is_parallel": true, "self": 0.0005611520000456949 } } } } } } }, "UnityEnvironment.step": { "total": 1246.8771518409494, "count": 231793, "is_parallel": true, "self": 38.55287018684453, "children": { "UnityEnvironment._generate_step_input": { "total": 80.37701672008649, "count": 231793, "is_parallel": true, "self": 80.37701672008649 }, "communicator.exchange": { "total": 1039.1284126049795, "count": 231793, "is_parallel": true, "self": 1039.1284126049795 }, "steps_from_proto": { "total": 88.81885232903886, "count": 231793, "is_parallel": true, "self": 32.836848532924876, "children": { "_process_rank_one_or_two_observation": { "total": 55.982003796113986, "count": 463586, "is_parallel": true, "self": 55.982003796113986 } } } } } } } } } } }, "trainer_advance": { "total": 486.98064429178953, "count": 231794, "self": 6.399004348841402, "children": { "process_trajectory": { "total": 148.86241286194866, "count": 231794, "self": 147.57177471694843, "children": { "RLTrainer._checkpoint": { "total": 1.29063814500023, "count": 10, "self": 1.29063814500023 } } }, "_update_policy": { "total": 331.7192270809995, "count": 97, "self": 268.8083516840032, "children": { "TorchPPOOptimizer.update": { "total": 62.91087539699629, "count": 2910, "self": 62.91087539699629 } } } } } } }, "trainer_threads": { "total": 1.1110000741609838e-06, "count": 1, "self": 1.1110000741609838e-06 }, "TrainerController._save_models": { "total": 0.11100855699987733, "count": 1, "self": 0.0021316030001798936, "children": { "RLTrainer._checkpoint": { "total": 0.10887695399969743, "count": 1, "self": 0.10887695399969743 } } } } } } }