{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3987427949905396, "min": 1.3987427949905396, "max": 1.4263802766799927, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71484.1484375, "min": 67758.953125, "max": 74537.5859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 107.94771241830065, "min": 84.87285223367698, "max": 397.8333333333333, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49548.0, "min": 48875.0, "max": 50238.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999914.0, "min": 49773.0, "max": 1999914.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999914.0, "min": 49773.0, "max": 1999914.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3295812606811523, "min": 0.12398172914981842, "max": 2.4372966289520264, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1069.27783203125, "min": 15.497715950012207, "max": 1415.306396484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4945291480727185, "min": 1.8040334973335266, "max": 4.07735217281047, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1603.9888789653778, "min": 225.50418716669083, "max": 2302.5686532258987, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4945291480727185, "min": 1.8040334973335266, "max": 4.07735217281047, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1603.9888789653778, "min": 225.50418716669083, "max": 2302.5686532258987, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015629897157648683, "min": 0.012487523874491067, "max": 0.020347788778195132, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04688969147294605, "min": 0.024975047748982133, "max": 0.061043366334585396, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04553158171474934, "min": 0.022610011603683235, "max": 0.06005283399588532, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13659474514424802, "min": 0.04522002320736647, "max": 0.18015850198765596, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1739989420333284e-06, "min": 3.1739989420333284e-06, "max": 0.00029532157655947494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.521996826099985e-06, "min": 9.521996826099985e-06, "max": 0.0008439285186904999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105796666666668, "min": 0.10105796666666668, "max": 0.19844052500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30317390000000005, "min": 0.20724370000000006, "max": 0.5813094999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.279253666666661e-05, "min": 6.279253666666661e-05, "max": 0.0049221821975, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018837760999999983, "min": 0.00018837760999999983, "max": 0.01406734405, "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": "1725224564", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Perro_byAdri-1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725226980" }, "total": 2416.515600392, "count": 1, "self": 0.42540485199970135, "children": { "run_training.setup": { "total": 0.05336980700008098, "count": 1, "self": 0.05336980700008098 }, "TrainerController.start_learning": { "total": 2416.036825733, "count": 1, "self": 4.697210716016798, "children": { "TrainerController._reset_env": { "total": 2.133933448999869, "count": 1, "self": 2.133933448999869 }, "TrainerController.advance": { "total": 2409.0899707969834, "count": 232038, "self": 4.795338150948737, "children": { "env_step": { "total": 1912.8728737079482, "count": 232038, "self": 1586.600393505891, "children": { "SubprocessEnvManager._take_step": { "total": 323.5246957770805, "count": 232038, "self": 15.990468621967466, "children": { "TorchPolicy.evaluate": { "total": 307.53422715511306, "count": 223083, "self": 307.53422715511306 } } }, "workers": { "total": 2.7477844249767713, "count": 232038, "self": 0.0, "children": { "worker_root": { "total": 2408.5574214939916, "count": 232038, "is_parallel": true, "self": 1108.8281505809582, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008804979997876217, "count": 1, "is_parallel": true, "self": 0.0002691779995984689, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006113200001891528, "count": 2, "is_parallel": true, "self": 0.0006113200001891528 } } }, "UnityEnvironment.step": { "total": 0.04300679200014201, "count": 1, "is_parallel": true, "self": 0.0002743919999375066, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021250400004646508, "count": 1, "is_parallel": true, "self": 0.00021250400004646508 }, "communicator.exchange": { "total": 0.04176385100004154, "count": 1, "is_parallel": true, "self": 0.04176385100004154 }, "steps_from_proto": { "total": 0.0007560450001165009, "count": 1, "is_parallel": true, "self": 0.0002055909999398864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005504540001766145, "count": 2, "is_parallel": true, "self": 0.0005504540001766145 } } } } } } }, "UnityEnvironment.step": { "total": 1299.7292709130334, "count": 232037, "is_parallel": true, "self": 39.98997879978924, "children": { "UnityEnvironment._generate_step_input": { "total": 86.61435337005537, "count": 232037, "is_parallel": true, "self": 86.61435337005537 }, "communicator.exchange": { "total": 1080.5364143451293, "count": 232037, "is_parallel": true, "self": 1080.5364143451293 }, "steps_from_proto": { "total": 92.58852439805946, "count": 232037, "is_parallel": true, "self": 34.384346060116286, "children": { "_process_rank_one_or_two_observation": { "total": 58.204178337943176, "count": 464074, "is_parallel": true, "self": 58.204178337943176 } } } } } } } } } } }, "trainer_advance": { "total": 491.42175893808644, "count": 232038, "self": 6.249312662079092, "children": { "process_trajectory": { "total": 146.00756528500847, "count": 232038, "self": 144.65810925300934, "children": { "RLTrainer._checkpoint": { "total": 1.3494560319991251, "count": 10, "self": 1.3494560319991251 } } }, "_update_policy": { "total": 339.1648809909989, "count": 97, "self": 276.39984902200854, "children": { "TorchPPOOptimizer.update": { "total": 62.76503196899034, "count": 2910, "self": 62.76503196899034 } } } } } } }, "trainer_threads": { "total": 9.159998626273591e-07, "count": 1, "self": 9.159998626273591e-07 }, "TrainerController._save_models": { "total": 0.1157098550002047, "count": 1, "self": 0.0019828610002150526, "children": { "RLTrainer._checkpoint": { "total": 0.11372699399998965, "count": 1, "self": 0.11372699399998965 } } } } } } }