{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4038923978805542, "min": 1.4038923978805542, "max": 1.426702618598938, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70867.0859375, "min": 67679.6015625, "max": 76655.8984375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 101.71517671517671, "min": 93.26553672316385, "max": 412.1967213114754, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48925.0, "min": 48846.0, "max": 50288.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999956.0, "min": 49730.0, "max": 1999956.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999956.0, "min": 49730.0, "max": 1999956.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4165987968444824, "min": 0.12907378375530243, "max": 2.4165987968444824, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1162.384033203125, "min": 15.617927551269531, "max": 1244.2626953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.71012433353432, "min": 1.967467321960394, "max": 3.869047755247926, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1784.569804430008, "min": 238.06354595720768, "max": 1982.9572799801826, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.71012433353432, "min": 1.967467321960394, "max": 3.869047755247926, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1784.569804430008, "min": 238.06354595720768, "max": 1982.9572799801826, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015386058627164958, "min": 0.013688114277708035, "max": 0.02093663349902878, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04615817588149487, "min": 0.02737622855541607, "max": 0.05737250922441793, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04834183131655057, "min": 0.0215398708358407, "max": 0.05961237798134486, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14502549394965172, "min": 0.0430797416716814, "max": 0.16779018094142278, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2868489044166703e-06, "min": 3.2868489044166703e-06, "max": 0.0002953262265579249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.860546713250011e-06, "min": 9.860546713250011e-06, "max": 0.0008439238686920499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109558333333331, "min": 0.10109558333333331, "max": 0.198442075, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30328674999999994, "min": 0.20733530000000003, "max": 0.5813079500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.466960833333341e-05, "min": 6.466960833333341e-05, "max": 0.004922259542500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019400882500000024, "min": 0.00019400882500000024, "max": 0.014067266705000003, "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": "1693400209", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693402685" }, "total": 2475.766404002, "count": 1, "self": 0.5667970480003532, "children": { "run_training.setup": { "total": 0.04609872699995776, "count": 1, "self": 0.04609872699995776 }, "TrainerController.start_learning": { "total": 2475.1535082269997, "count": 1, "self": 4.581738799012328, "children": { "TrainerController._reset_env": { "total": 4.240234814000019, "count": 1, "self": 4.240234814000019 }, "TrainerController.advance": { "total": 2466.205299755987, "count": 231372, "self": 4.66457841404781, "children": { "env_step": { "total": 1903.621046312935, "count": 231372, "self": 1610.7536220219822, "children": { "SubprocessEnvManager._take_step": { "total": 289.8935524189694, "count": 231372, "self": 17.077325626954348, "children": { "TorchPolicy.evaluate": { "total": 272.8162267920151, "count": 222990, "self": 272.8162267920151 } } }, "workers": { "total": 2.9738718719834196, "count": 231372, "self": 0.0, "children": { "worker_root": { "total": 2467.4906193049696, "count": 231372, "is_parallel": true, "self": 1150.5548111259282, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008947200000193334, "count": 1, "is_parallel": true, "self": 0.0002661550001903379, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006285649998289955, "count": 2, "is_parallel": true, "self": 0.0006285649998289955 } } }, "UnityEnvironment.step": { "total": 0.02956558400001086, "count": 1, "is_parallel": true, "self": 0.0003352410000161399, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020750099997712823, "count": 1, "is_parallel": true, "self": 0.00020750099997712823 }, "communicator.exchange": { "total": 0.028264688000035676, "count": 1, "is_parallel": true, "self": 0.028264688000035676 }, "steps_from_proto": { "total": 0.0007581539999819142, "count": 1, "is_parallel": true, "self": 0.0002155380000203877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005426159999615265, "count": 2, "is_parallel": true, "self": 0.0005426159999615265 } } } } } } }, "UnityEnvironment.step": { "total": 1316.9358081790415, "count": 231371, "is_parallel": true, "self": 40.65206076595996, "children": { "UnityEnvironment._generate_step_input": { "total": 82.98047620100374, "count": 231371, "is_parallel": true, "self": 82.98047620100374 }, "communicator.exchange": { "total": 1093.8207630180693, "count": 231371, "is_parallel": true, "self": 1093.8207630180693 }, "steps_from_proto": { "total": 99.48250819400835, "count": 231371, "is_parallel": true, "self": 35.184810098876255, "children": { "_process_rank_one_or_two_observation": { "total": 64.29769809513209, "count": 462742, "is_parallel": true, "self": 64.29769809513209 } } } } } } } } } } }, "trainer_advance": { "total": 557.9196750290045, "count": 231372, "self": 6.69008749703346, "children": { "process_trajectory": { "total": 136.11346017097014, "count": 231372, "self": 134.90415955197057, "children": { "RLTrainer._checkpoint": { "total": 1.2093006189995776, "count": 10, "self": 1.2093006189995776 } } }, "_update_policy": { "total": 415.11612736100085, "count": 97, "self": 353.7989755110124, "children": { "TorchPPOOptimizer.update": { "total": 61.31715184998848, "count": 2910, "self": 61.31715184998848 } } } } } } }, "trainer_threads": { "total": 8.560000424040481e-07, "count": 1, "self": 8.560000424040481e-07 }, "TrainerController._save_models": { "total": 0.1262340020002739, "count": 1, "self": 0.0019845580004584917, "children": { "RLTrainer._checkpoint": { "total": 0.12424944399981541, "count": 1, "self": 0.12424944399981541 } } } } } } }