{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4016183614730835, "min": 1.4016183614730835, "max": 1.429039478302002, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71618.4921875, "min": 68416.9375, "max": 76358.53125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.33105802047781, "min": 77.61006289308176, "max": 386.04615384615386, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49418.0, "min": 49303.0, "max": 50186.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999957.0, "min": 49834.0, "max": 1999957.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999957.0, "min": 49834.0, "max": 1999957.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.414539098739624, "min": 0.05287278816103935, "max": 2.4720962047576904, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1414.919921875, "min": 6.820589542388916, "max": 1541.808349609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7124319603418736, "min": 1.844498962279438, "max": 3.9577890626745287, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2175.485128760338, "min": 237.9403661340475, "max": 2450.7124643325806, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7124319603418736, "min": 1.844498962279438, "max": 3.9577890626745287, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2175.485128760338, "min": 237.9403661340475, "max": 2450.7124643325806, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01655630690495147, "min": 0.013929722543495397, "max": 0.019668362911518973, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04966892071485442, "min": 0.027859445086990793, "max": 0.05606024116956784, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051025004436572395, "min": 0.02261689690252145, "max": 0.07482540868222713, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15307501330971718, "min": 0.0452337938050429, "max": 0.21638623798886936, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4934488355500053e-06, "min": 3.4934488355500053e-06, "max": 0.000295347526550825, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0480346506650016e-05, "min": 1.0480346506650016e-05, "max": 0.000844143018619, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116445, "min": 0.10116445, "max": 0.1984491750000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30349335, "min": 0.2075182, "max": 0.5813810000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.810605500000011e-05, "min": 6.810605500000011e-05, "max": 0.0049226138325000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002043181650000003, "min": 0.0002043181650000003, "max": 0.014070911900000002, "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": "1678224119", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "1.22.4", "end_time_seconds": "1678226555" }, "total": 2435.725859467, "count": 1, "self": 0.4412880459999542, "children": { "run_training.setup": { "total": 0.11208064200002354, "count": 1, "self": 0.11208064200002354 }, "TrainerController.start_learning": { "total": 2435.1724907790003, "count": 1, "self": 4.282834502935657, "children": { "TrainerController._reset_env": { "total": 10.46941585799999, "count": 1, "self": 10.46941585799999 }, "TrainerController.advance": { "total": 2420.299546449065, "count": 232825, "self": 4.560012761201506, "children": { "env_step": { "total": 1873.5455306199426, "count": 232825, "self": 1563.7748840159636, "children": { "SubprocessEnvManager._take_step": { "total": 306.899889093974, "count": 232825, "self": 16.300362326971992, "children": { "TorchPolicy.evaluate": { "total": 290.59952676700203, "count": 223077, "self": 73.36514302500404, "children": { "TorchPolicy.sample_actions": { "total": 217.234383741998, "count": 223077, "self": 217.234383741998 } } } } }, "workers": { "total": 2.870757510004978, "count": 232825, "self": 0.0, "children": { "worker_root": { "total": 2426.7499920290134, "count": 232825, "is_parallel": true, "self": 1156.740721588191, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008469260000083523, "count": 1, "is_parallel": true, "self": 0.0002957170000286169, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005512089999797354, "count": 2, "is_parallel": true, "self": 0.0005512089999797354 } } }, "UnityEnvironment.step": { "total": 0.04141029200002322, "count": 1, "is_parallel": true, "self": 0.0002945870000985451, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019582400000217604, "count": 1, "is_parallel": true, "self": 0.00019582400000217604 }, "communicator.exchange": { "total": 0.04013729599995486, "count": 1, "is_parallel": true, "self": 0.04013729599995486 }, "steps_from_proto": { "total": 0.0007825849999676393, "count": 1, "is_parallel": true, "self": 0.0002555279999114646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005270570000561747, "count": 2, "is_parallel": true, "self": 0.0005270570000561747 } } } } } } }, "UnityEnvironment.step": { "total": 1270.0092704408223, "count": 232824, "is_parallel": true, "self": 38.51624715301682, "children": { "UnityEnvironment._generate_step_input": { "total": 78.80901931488273, "count": 232824, "is_parallel": true, "self": 78.80901931488273 }, "communicator.exchange": { "total": 1060.9074607320335, "count": 232824, "is_parallel": true, "self": 1060.9074607320335 }, "steps_from_proto": { "total": 91.77654324088905, "count": 232824, "is_parallel": true, "self": 36.872269554863294, "children": { "_process_rank_one_or_two_observation": { "total": 54.90427368602576, "count": 465648, "is_parallel": true, "self": 54.90427368602576 } } } } } } } } } } }, "trainer_advance": { "total": 542.1940030679207, "count": 232825, "self": 6.511636836833759, "children": { "process_trajectory": { "total": 171.00697057108675, "count": 232825, "self": 169.55342758408722, "children": { "RLTrainer._checkpoint": { "total": 1.4535429869995369, "count": 10, "self": 1.4535429869995369 } } }, "_update_policy": { "total": 364.6753956600001, "count": 97, "self": 305.04166708500014, "children": { "TorchPPOOptimizer.update": { "total": 59.633728574999964, "count": 2910, "self": 59.633728574999964 } } } } } } }, "trainer_threads": { "total": 8.289998731925152e-07, "count": 1, "self": 8.289998731925152e-07 }, "TrainerController._save_models": { "total": 0.12069313999973019, "count": 1, "self": 0.0020291199998609954, "children": { "RLTrainer._checkpoint": { "total": 0.1186640199998692, "count": 1, "self": 0.1186640199998692 } } } } } } }