{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407686471939087, "min": 1.407686471939087, "max": 1.4281586408615112, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68703.546875, "min": 68564.421875, "max": 77948.359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.86213235294117, "min": 84.38461538461539, "max": 396.92913385826773, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49429.0, "min": 49122.0, "max": 50410.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999954.0, "min": 49814.0, "max": 1999954.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999954.0, "min": 49814.0, "max": 1999954.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.388575553894043, "min": 0.01320489589124918, "max": 2.4594802856445312, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1299.3851318359375, "min": 1.6638169288635254, "max": 1379.4686279296875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7419488443171276, "min": 1.8689357943478084, "max": 3.9063646756451855, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2035.6201713085175, "min": 235.48591008782387, "max": 2169.014094889164, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7419488443171276, "min": 1.8689357943478084, "max": 3.9063646756451855, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2035.6201713085175, "min": 235.48591008782387, "max": 2169.014094889164, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017973322317832045, "min": 0.013226937520327435, "max": 0.01956920241322627, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.053919966953496136, "min": 0.02645387504065487, "max": 0.05870760723967881, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05170359400411447, "min": 0.022990238149132994, "max": 0.05489820254345735, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1551107820123434, "min": 0.04833087362349034, "max": 0.16291377072532973, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4516988494666646e-06, "min": 3.4516988494666646e-06, "max": 0.000295327276557575, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0355096548399993e-05, "min": 1.0355096548399993e-05, "max": 0.0008441484186171999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115053333333335, "min": 0.10115053333333335, "max": 0.19844242500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30345160000000004, "min": 0.20742670000000002, "max": 0.5813828000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.741161333333335e-05, "min": 6.741161333333335e-05, "max": 0.0049222770075, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020223484000000003, "min": 0.00020223484000000003, "max": 0.01407100172, "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": "1670961671", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \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=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": "1.21.6", "end_time_seconds": "1670963924" }, "total": 2252.7400932299997, "count": 1, "self": 0.3962675759994454, "children": { "run_training.setup": { "total": 0.11476383900003384, "count": 1, "self": 0.11476383900003384 }, "TrainerController.start_learning": { "total": 2252.229061815, "count": 1, "self": 3.882184409023921, "children": { "TrainerController._reset_env": { "total": 10.083884673, "count": 1, "self": 10.083884673 }, "TrainerController.advance": { "total": 2238.147155857976, "count": 231751, "self": 4.08876219299691, "children": { "env_step": { "total": 1768.7174794140162, "count": 231751, "self": 1480.15377697095, "children": { "SubprocessEnvManager._take_step": { "total": 285.90468336006626, "count": 231751, "self": 14.900519066079426, "children": { "TorchPolicy.evaluate": { "total": 271.00416429398683, "count": 222927, "self": 67.22938684796168, "children": { "TorchPolicy.sample_actions": { "total": 203.77477744602515, "count": 222927, "self": 203.77477744602515 } } } } }, "workers": { "total": 2.659019082999862, "count": 231751, "self": 0.0, "children": { "worker_root": { "total": 2244.200678631045, "count": 231751, "is_parallel": true, "self": 1029.5116031930086, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003435244000002058, "count": 1, "is_parallel": true, "self": 0.00038348399999676985, "children": { "_process_rank_one_or_two_observation": { "total": 0.003051760000005288, "count": 2, "is_parallel": true, "self": 0.003051760000005288 } } }, "UnityEnvironment.step": { "total": 0.027502957999956834, "count": 1, "is_parallel": true, "self": 0.00027710699993122034, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018295500001386245, "count": 1, "is_parallel": true, "self": 0.00018295500001386245 }, "communicator.exchange": { "total": 0.026328293000005942, "count": 1, "is_parallel": true, "self": 0.026328293000005942 }, "steps_from_proto": { "total": 0.000714603000005809, "count": 1, "is_parallel": true, "self": 0.00024963999999272346, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046496300001308555, "count": 2, "is_parallel": true, "self": 0.00046496300001308555 } } } } } } }, "UnityEnvironment.step": { "total": 1214.6890754380363, "count": 231750, "is_parallel": true, "self": 36.02532519519468, "children": { "UnityEnvironment._generate_step_input": { "total": 80.9331709959734, "count": 231750, "is_parallel": true, "self": 80.9331709959734 }, "communicator.exchange": { "total": 1000.3100786899265, "count": 231750, "is_parallel": true, "self": 1000.3100786899265 }, "steps_from_proto": { "total": 97.42050055694182, "count": 231750, "is_parallel": true, "self": 42.66117536178251, "children": { "_process_rank_one_or_two_observation": { "total": 54.759325195159306, "count": 463500, "is_parallel": true, "self": 54.759325195159306 } } } } } } } } } } }, "trainer_advance": { "total": 465.34091425096267, "count": 231751, "self": 6.214561086949402, "children": { "process_trajectory": { "total": 152.6539491730142, "count": 231751, "self": 152.1603290700141, "children": { "RLTrainer._checkpoint": { "total": 0.4936201030001257, "count": 4, "self": 0.4936201030001257 } } }, "_update_policy": { "total": 306.47240399099906, "count": 97, "self": 253.30546490499722, "children": { "TorchPPOOptimizer.update": { "total": 53.16693908600183, "count": 2910, "self": 53.16693908600183 } } } } } } }, "trainer_threads": { "total": 1.0140001904801466e-06, "count": 1, "self": 1.0140001904801466e-06 }, "TrainerController._save_models": { "total": 0.1158358610000505, "count": 1, "self": 0.002028074000008928, "children": { "RLTrainer._checkpoint": { "total": 0.11380778700004157, "count": 1, "self": 0.11380778700004157 } } } } } } }