{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3773263692855835, "min": 1.3773263692855835, "max": 1.4231269359588623, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68070.2265625, "min": 68070.2265625, "max": 76697.90625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.10648148148148, "min": 73.13224368499257, "max": 397.57936507936506, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49317.0, "min": 48834.0, "max": 50095.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999936.0, "min": 49713.0, "max": 1999936.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999936.0, "min": 49713.0, "max": 1999936.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.514389753341675, "min": 0.04993633180856705, "max": 2.5256264209747314, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1629.3245849609375, "min": 6.24204158782959, "max": 1639.748046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.926974509877187, "min": 1.8267483329772949, "max": 4.0519389970914315, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2544.6794824004173, "min": 228.34354162216187, "max": 2585.1397720575333, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.926974509877187, "min": 1.8267483329772949, "max": 4.0519389970914315, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2544.6794824004173, "min": 228.34354162216187, "max": 2585.1397720575333, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015472133636164169, "min": 0.013561197902163258, "max": 0.019518072229645137, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04641640090849251, "min": 0.027122395804326516, "max": 0.058554216688935415, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05165168102830648, "min": 0.020431418798398226, "max": 0.05536146673063438, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15495504308491945, "min": 0.04086283759679645, "max": 0.16608440019190313, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.620648793150012e-06, "min": 3.620648793150012e-06, "max": 0.00029530110156629995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0861946379450036e-05, "min": 1.0861946379450036e-05, "max": 0.0008438320687226498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120685, "min": 0.10120685, "max": 0.1984337, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30362055, "min": 0.20755740000000003, "max": 0.58127735, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.02218150000002e-05, "min": 7.02218150000002e-05, "max": 0.00492184163, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002106654450000006, "min": 0.0002106654450000006, "max": 0.014065739765, "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": "1670381209", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=zl-Huggy-01 --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": "1.21.6", "end_time_seconds": "1670383689" }, "total": 2479.4554283260004, "count": 1, "self": 0.4410988940007883, "children": { "run_training.setup": { "total": 0.1112992599998961, "count": 1, "self": 0.1112992599998961 }, "TrainerController.start_learning": { "total": 2478.903030172, "count": 1, "self": 4.4074491239302915, "children": { "TrainerController._reset_env": { "total": 9.851468468999883, "count": 1, "self": 9.851468468999883 }, "TrainerController.advance": { "total": 2464.48457436807, "count": 233192, "self": 4.553547679026451, "children": { "env_step": { "total": 1857.0126117689854, "count": 233192, "self": 1540.7918200229421, "children": { "SubprocessEnvManager._take_step": { "total": 313.39049901499743, "count": 233192, "self": 15.574790799073071, "children": { "TorchPolicy.evaluate": { "total": 297.81570821592436, "count": 222920, "self": 71.07128135381777, "children": { "TorchPolicy.sample_actions": { "total": 226.7444268621066, "count": 222920, "self": 226.7444268621066 } } } } }, "workers": { "total": 2.8302927310458017, "count": 233192, "self": 0.0, "children": { "worker_root": { "total": 2470.34284792792, "count": 233192, "is_parallel": true, "self": 1209.000966229926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001907788999915283, "count": 1, "is_parallel": true, "self": 0.00034060400002999813, "children": { "_process_rank_one_or_two_observation": { "total": 0.001567184999885285, "count": 2, "is_parallel": true, "self": 0.001567184999885285 } } }, "UnityEnvironment.step": { "total": 0.028911758000049304, "count": 1, "is_parallel": true, "self": 0.0003004950001468387, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019699499989656033, "count": 1, "is_parallel": true, "self": 0.00019699499989656033 }, "communicator.exchange": { "total": 0.027691273000073124, "count": 1, "is_parallel": true, "self": 0.027691273000073124 }, "steps_from_proto": { "total": 0.00072299499993278, "count": 1, "is_parallel": true, "self": 0.0002562779998243059, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046671700010847417, "count": 2, "is_parallel": true, "self": 0.00046671700010847417 } } } } } } }, "UnityEnvironment.step": { "total": 1261.341881697994, "count": 233191, "is_parallel": true, "self": 35.35063704581762, "children": { "UnityEnvironment._generate_step_input": { "total": 79.23386435201633, "count": 233191, "is_parallel": true, "self": 79.23386435201633 }, "communicator.exchange": { "total": 1048.9433284920326, "count": 233191, "is_parallel": true, "self": 1048.9433284920326 }, "steps_from_proto": { "total": 97.81405180812749, "count": 233191, "is_parallel": true, "self": 42.275648078221366, "children": { "_process_rank_one_or_two_observation": { "total": 55.53840372990612, "count": 466382, "is_parallel": true, "self": 55.53840372990612 } } } } } } } } } } }, "trainer_advance": { "total": 602.9184149200578, "count": 233192, "self": 6.57727992100331, "children": { "process_trajectory": { "total": 166.4084211680506, "count": 233192, "self": 165.77136076605075, "children": { "RLTrainer._checkpoint": { "total": 0.6370604019998609, "count": 4, "self": 0.6370604019998609 } } }, "_update_policy": { "total": 429.93271383100387, "count": 97, "self": 346.5880613409988, "children": { "TorchPPOOptimizer.update": { "total": 83.34465249000505, "count": 3880, "self": 83.34465249000505 } } } } } } }, "trainer_threads": { "total": 8.229999366449192e-07, "count": 1, "self": 8.229999366449192e-07 }, "TrainerController._save_models": { "total": 0.15953738799998973, "count": 1, "self": 0.0027015379996555566, "children": { "RLTrainer._checkpoint": { "total": 0.15683585000033418, "count": 1, "self": 0.15683585000033418 } } } } } } }