{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4022955894470215, "min": 1.4022955894470215, "max": 1.4265077114105225, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70463.953125, "min": 68753.0, "max": 78826.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.02662229617304, "min": 80.0032414910859, "max": 403.11290322580646, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48697.0, "min": 48697.0, "max": 50048.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999882.0, "min": 49891.0, "max": 1999882.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999882.0, "min": 49891.0, "max": 1999882.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.450028419494629, "min": 0.02572472207248211, "max": 2.4853744506835938, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1472.467041015625, "min": 3.1641407012939453, "max": 1506.136962890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8154625390809707, "min": 1.7073662012088588, "max": 4.06211147646072, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2293.0929859876633, "min": 210.00604274868965, "max": 2366.007886469364, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8154625390809707, "min": 1.7073662012088588, "max": 4.06211147646072, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2293.0929859876633, "min": 210.00604274868965, "max": 2366.007886469364, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01764521817676723, "min": 0.014901650791742013, "max": 0.019558076519024324, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05293565453030169, "min": 0.030084984868881295, "max": 0.05530508271573733, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054394113396604854, "min": 0.02273490677277247, "max": 0.06590359484155973, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16318234018981456, "min": 0.04546981354554494, "max": 0.1841067098081112, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.502948832383336e-06, "min": 3.502948832383336e-06, "max": 0.0002953229265590249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0508846497150007e-05, "min": 1.0508846497150007e-05, "max": 0.0008439348186883999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116761666666668, "min": 0.10116761666666668, "max": 0.19844097500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30350285000000005, "min": 0.20747925, "max": 0.5813115999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.826407166666671e-05, "min": 6.826407166666671e-05, "max": 0.0049222046525000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020479221500000012, "min": 0.00020479221500000012, "max": 0.014067448839999996, "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": "1680694567", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1680696895" }, "total": 2328.4334920630004, "count": 1, "self": 0.452826492999975, "children": { "run_training.setup": { "total": 0.11700423799999271, "count": 1, "self": 0.11700423799999271 }, "TrainerController.start_learning": { "total": 2327.8636613320004, "count": 1, "self": 4.292943676978666, "children": { "TrainerController._reset_env": { "total": 3.911563242999989, "count": 1, "self": 3.911563242999989 }, "TrainerController.advance": { "total": 2319.5278991170217, "count": 232601, "self": 4.819121903039559, "children": { "env_step": { "total": 1815.7108490109774, "count": 232601, "self": 1535.182158056904, "children": { "SubprocessEnvManager._take_step": { "total": 277.7073810560372, "count": 232601, "self": 16.30108468105243, "children": { "TorchPolicy.evaluate": { "total": 261.4062963749848, "count": 222970, "self": 261.4062963749848 } } }, "workers": { "total": 2.821309898036361, "count": 232601, "self": 0.0, "children": { "worker_root": { "total": 2319.738149926963, "count": 232601, "is_parallel": true, "self": 1063.2782324819975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009123560000148245, "count": 1, "is_parallel": true, "self": 0.0002490539999939756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006633020000208489, "count": 2, "is_parallel": true, "self": 0.0006633020000208489 } } }, "UnityEnvironment.step": { "total": 0.02969366499996795, "count": 1, "is_parallel": true, "self": 0.00030203499994740923, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003806160000294767, "count": 1, "is_parallel": true, "self": 0.0003806160000294767 }, "communicator.exchange": { "total": 0.02831046400001469, "count": 1, "is_parallel": true, "self": 0.02831046400001469 }, "steps_from_proto": { "total": 0.0007005499999763742, "count": 1, "is_parallel": true, "self": 0.0002218729999867719, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047867699998960234, "count": 2, "is_parallel": true, "self": 0.00047867699998960234 } } } } } } }, "UnityEnvironment.step": { "total": 1256.4599174449656, "count": 232600, "is_parallel": true, "self": 38.544454521831994, "children": { "UnityEnvironment._generate_step_input": { "total": 80.00192520910042, "count": 232600, "is_parallel": true, "self": 80.00192520910042 }, "communicator.exchange": { "total": 1048.3896509950355, "count": 232600, "is_parallel": true, "self": 1048.3896509950355 }, "steps_from_proto": { "total": 89.52388671899774, "count": 232600, "is_parallel": true, "self": 33.60960061004914, "children": { "_process_rank_one_or_two_observation": { "total": 55.9142861089486, "count": 465200, "is_parallel": true, "self": 55.9142861089486 } } } } } } } } } } }, "trainer_advance": { "total": 498.9979282030047, "count": 232601, "self": 6.5088459118545074, "children": { "process_trajectory": { "total": 131.18770495015116, "count": 232601, "self": 129.80657951015104, "children": { "RLTrainer._checkpoint": { "total": 1.381125440000119, "count": 10, "self": 1.381125440000119 } } }, "_update_policy": { "total": 361.301377340999, "count": 97, "self": 302.45071363299684, "children": { "TorchPPOOptimizer.update": { "total": 58.85066370800217, "count": 2910, "self": 58.85066370800217 } } } } } } }, "trainer_threads": { "total": 1.2300001799303573e-06, "count": 1, "self": 1.2300001799303573e-06 }, "TrainerController._save_models": { "total": 0.13125406500012105, "count": 1, "self": 0.0022504070002469234, "children": { "RLTrainer._checkpoint": { "total": 0.12900365799987412, "count": 1, "self": 0.12900365799987412 } } } } } } }