{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4072707891464233, "min": 1.4072707891464233, "max": 1.433038592338562, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71120.6484375, "min": 68836.65625, "max": 77597.2890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 114.30751708428247, "min": 89.54710144927536, "max": 380.80916030534354, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50181.0, "min": 48773.0, "max": 50247.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999921.0, "min": 49765.0, "max": 1999921.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999921.0, "min": 49765.0, "max": 1999921.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4373295307159424, "min": 0.1493716835975647, "max": 2.459739923477173, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1069.9876708984375, "min": 19.418319702148438, "max": 1336.135498046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7631693487829936, "min": 1.925937588283649, "max": 3.885508327208685, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1652.031344115734, "min": 250.37188647687435, "max": 2076.707936167717, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7631693487829936, "min": 1.925937588283649, "max": 3.885508327208685, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1652.031344115734, "min": 250.37188647687435, "max": 2076.707936167717, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01375971577734971, "min": 0.01375971577734971, "max": 0.02142375018568904, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.041279147332049126, "min": 0.028885050307872008, "max": 0.06427125055706712, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.044468293918503654, "min": 0.021265685682495435, "max": 0.062020429968833925, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13340488175551096, "min": 0.04253137136499087, "max": 0.18606128990650178, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1489489503833366e-06, "min": 3.1489489503833366e-06, "max": 0.000295332526555825, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.44684685115001e-06, "min": 9.44684685115001e-06, "max": 0.0008441793186069001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10104961666666668, "min": 0.10104961666666668, "max": 0.198444175, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30314885, "min": 0.20725970000000005, "max": 0.5813931, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.237587166666673e-05, "min": 6.237587166666673e-05, "max": 0.004922364332500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018712761500000018, "min": 0.00018712761500000018, "max": 0.014071515690000001, "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": "1670354663", "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=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": "1670356864" }, "total": 2201.666623001, "count": 1, "self": 0.38779205899982117, "children": { "run_training.setup": { "total": 0.10272763199986912, "count": 1, "self": 0.10272763199986912 }, "TrainerController.start_learning": { "total": 2201.17610331, "count": 1, "self": 3.953459898967594, "children": { "TrainerController._reset_env": { "total": 9.736971284999981, "count": 1, "self": 9.736971284999981 }, "TrainerController.advance": { "total": 2187.3577135130326, "count": 231557, "self": 4.265732070992726, "children": { "env_step": { "total": 1709.729791700011, "count": 231557, "self": 1412.5024204621375, "children": { "SubprocessEnvManager._take_step": { "total": 294.7677167128859, "count": 231557, "self": 14.68241245079821, "children": { "TorchPolicy.evaluate": { "total": 280.0853042620877, "count": 223068, "self": 68.52710855703913, "children": { "TorchPolicy.sample_actions": { "total": 211.55819570504855, "count": 223068, "self": 211.55819570504855 } } } } }, "workers": { "total": 2.459654524987627, "count": 231557, "self": 0.0, "children": { "worker_root": { "total": 2193.4556394939373, "count": 231557, "is_parallel": true, "self": 1033.7061584048681, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017782869999791728, "count": 1, "is_parallel": true, "self": 0.0003453850001733372, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014329019998058357, "count": 2, "is_parallel": true, "self": 0.0014329019998058357 } } }, "UnityEnvironment.step": { "total": 0.02708667100000639, "count": 1, "is_parallel": true, "self": 0.00032594999993307283, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019732800001293072, "count": 1, "is_parallel": true, "self": 0.00019732800001293072 }, "communicator.exchange": { "total": 0.025813648999928773, "count": 1, "is_parallel": true, "self": 0.025813648999928773 }, "steps_from_proto": { "total": 0.0007497440001316136, "count": 1, "is_parallel": true, "self": 0.00023739100015518488, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005123529999764287, "count": 2, "is_parallel": true, "self": 0.0005123529999764287 } } } } } } }, "UnityEnvironment.step": { "total": 1159.7494810890691, "count": 231556, "is_parallel": true, "self": 34.027145589229804, "children": { "UnityEnvironment._generate_step_input": { "total": 76.28065858795344, "count": 231556, "is_parallel": true, "self": 76.28065858795344 }, "communicator.exchange": { "total": 959.0963848209715, "count": 231556, "is_parallel": true, "self": 959.0963848209715 }, "steps_from_proto": { "total": 90.34529209091443, "count": 231556, "is_parallel": true, "self": 37.560044136883334, "children": { "_process_rank_one_or_two_observation": { "total": 52.78524795403109, "count": 463112, "is_parallel": true, "self": 52.78524795403109 } } } } } } } } } } }, "trainer_advance": { "total": 473.36218974202893, "count": 231557, "self": 5.9659846399652, "children": { "process_trajectory": { "total": 147.6407988070648, "count": 231557, "self": 147.15054745106409, "children": { "RLTrainer._checkpoint": { "total": 0.49025135600072645, "count": 4, "self": 0.49025135600072645 } } }, "_update_policy": { "total": 319.7554062949989, "count": 97, "self": 265.01072785098654, "children": { "TorchPPOOptimizer.update": { "total": 54.74467844401238, "count": 2910, "self": 54.74467844401238 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.12795766699991873, "count": 1, "self": 0.001965056000244658, "children": { "RLTrainer._checkpoint": { "total": 0.12599261099967407, "count": 1, "self": 0.12599261099967407 } } } } } } }