{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4056673049926758, "min": 1.4056673049926758, "max": 1.430708885192871, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71919.5625, "min": 68464.0625, "max": 78072.515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.25925925925925, "min": 93.49527410207939, "max": 368.77037037037036, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50184.0, "min": 48804.0, "max": 50350.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999992.0, "min": 49866.0, "max": 1999992.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999992.0, "min": 49866.0, "max": 1999992.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3469860553741455, "min": 0.017784278839826584, "max": 2.42008900642395, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1140.63525390625, "min": 2.436446189880371, "max": 1246.785400390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.656336315006876, "min": 1.8529174482300335, "max": 3.799275526995601, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1776.9794490933418, "min": 253.84969040751457, "max": 1884.6119043827057, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.656336315006876, "min": 1.8529174482300335, "max": 3.799275526995601, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1776.9794490933418, "min": 253.84969040751457, "max": 1884.6119043827057, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014654411519101511, "min": 0.013525732476167226, "max": 0.02084803735294069, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.029308823038203022, "min": 0.02705146495233445, "max": 0.05748982474130268, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05198853351175785, "min": 0.02175226714462042, "max": 0.06205614792803923, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1039770670235157, "min": 0.04350453428924084, "max": 0.18616844378411768, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.6104984631999965e-06, "min": 4.6104984631999965e-06, "max": 0.00029530672656442506, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.220996926399993e-06, "min": 9.220996926399993e-06, "max": 0.0008442487685837501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10153680000000001, "min": 0.10153680000000001, "max": 0.198435575, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20307360000000002, "min": 0.20307360000000002, "max": 0.5814162500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.668631999999998e-05, "min": 8.668631999999998e-05, "max": 0.004921935192500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017337263999999997, "min": 0.00017337263999999997, "max": 0.014072670875000004, "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": "1714073629", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714076209" }, "total": 2579.9167474829997, "count": 1, "self": 0.4895115419994909, "children": { "run_training.setup": { "total": 0.08846238500007075, "count": 1, "self": 0.08846238500007075 }, "TrainerController.start_learning": { "total": 2579.338773556, "count": 1, "self": 4.604408637012966, "children": { "TrainerController._reset_env": { "total": 2.9654170379999414, "count": 1, "self": 2.9654170379999414 }, "TrainerController.advance": { "total": 2571.649080812987, "count": 231069, "self": 4.878382835135653, "children": { "env_step": { "total": 2090.1446619779026, "count": 231069, "self": 1731.525330326031, "children": { "SubprocessEnvManager._take_step": { "total": 355.39671416390456, "count": 231069, "self": 19.075466327900358, "children": { "TorchPolicy.evaluate": { "total": 336.3212478360042, "count": 223019, "self": 336.3212478360042 } } }, "workers": { "total": 3.2226174879671134, "count": 231069, "self": 0.0, "children": { "worker_root": { "total": 2571.5826449540177, "count": 231069, "is_parallel": true, "self": 1178.1025901690834, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009767960000317544, "count": 1, "is_parallel": true, "self": 0.0002775809999775447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006992150000542097, "count": 2, "is_parallel": true, "self": 0.0006992150000542097 } } }, "UnityEnvironment.step": { "total": 0.03180550900003709, "count": 1, "is_parallel": true, "self": 0.00042142899997088534, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021636100007071946, "count": 1, "is_parallel": true, "self": 0.00021636100007071946 }, "communicator.exchange": { "total": 0.030320886000026803, "count": 1, "is_parallel": true, "self": 0.030320886000026803 }, "steps_from_proto": { "total": 0.000846832999968683, "count": 1, "is_parallel": true, "self": 0.0002417439999362614, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006050890000324216, "count": 2, "is_parallel": true, "self": 0.0006050890000324216 } } } } } } }, "UnityEnvironment.step": { "total": 1393.4800547849343, "count": 231068, "is_parallel": true, "self": 41.583538315890564, "children": { "UnityEnvironment._generate_step_input": { "total": 91.62019090607225, "count": 231068, "is_parallel": true, "self": 91.62019090607225 }, "communicator.exchange": { "total": 1160.9794712879968, "count": 231068, "is_parallel": true, "self": 1160.9794712879968 }, "steps_from_proto": { "total": 99.29685427497475, "count": 231068, "is_parallel": true, "self": 37.620524219094364, "children": { "_process_rank_one_or_two_observation": { "total": 61.676330055880385, "count": 462136, "is_parallel": true, "self": 61.676330055880385 } } } } } } } } } } }, "trainer_advance": { "total": 476.62603599994884, "count": 231069, "self": 7.244574380962604, "children": { "process_trajectory": { "total": 159.65623101998688, "count": 231069, "self": 158.19028733898688, "children": { "RLTrainer._checkpoint": { "total": 1.4659436809999988, "count": 10, "self": 1.4659436809999988 } } }, "_update_policy": { "total": 309.72523059899936, "count": 96, "self": 247.12286658401467, "children": { "TorchPPOOptimizer.update": { "total": 62.60236401498469, "count": 2880, "self": 62.60236401498469 } } } } } } }, "trainer_threads": { "total": 8.990000424091704e-07, "count": 1, "self": 8.990000424091704e-07 }, "TrainerController._save_models": { "total": 0.11986616900003355, "count": 1, "self": 0.0019689199998538243, "children": { "RLTrainer._checkpoint": { "total": 0.11789724900017973, "count": 1, "self": 0.11789724900017973 } } } } } } }