{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4063256978988647, "min": 1.4063256978988647, "max": 1.429353952407837, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70226.28125, "min": 68755.8515625, "max": 77525.78125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.9304897314376, "min": 77.38161993769471, "max": 413.95081967213116, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49330.0, "min": 48924.0, "max": 50502.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999956.0, "min": 49874.0, "max": 1999956.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999956.0, "min": 49874.0, "max": 1999956.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4412081241607666, "min": 0.08094997704029083, "max": 2.484259843826294, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1545.28466796875, "min": 9.794947624206543, "max": 1551.4227294921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8361855710475554, "min": 1.761910484103132, "max": 3.985196542681048, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2428.3054664731026, "min": 213.19116857647896, "max": 2428.3054664731026, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8361855710475554, "min": 1.761910484103132, "max": 3.985196542681048, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2428.3054664731026, "min": 213.19116857647896, "max": 2428.3054664731026, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01710995665198425, "min": 0.013427512719257115, "max": 0.019814353756373748, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05132986995595275, "min": 0.02685502543851423, "max": 0.058560732098218674, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05519077856507567, "min": 0.022408453437189262, "max": 0.06613522072633107, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.165572335695227, "min": 0.044945931807160375, "max": 0.19840566217899322, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.911198696300001e-06, "min": 3.911198696300001e-06, "max": 0.00029537242654252495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1733596088900002e-05, "min": 1.1733596088900002e-05, "max": 0.0008442087185970998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10130370000000001, "min": 0.10130370000000001, "max": 0.19845747500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30391110000000005, "min": 0.20773960000000002, "max": 0.5814029, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.505463000000001e-05, "min": 7.505463000000001e-05, "max": 0.004923028002500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022516389000000003, "min": 0.00022516389000000003, "max": 0.014072004709999999, "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": "1670754049", "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": "1670756340" }, "total": 2291.4338983959997, "count": 1, "self": 0.39118446299971765, "children": { "run_training.setup": { "total": 0.17597635600003514, "count": 1, "self": 0.17597635600003514 }, "TrainerController.start_learning": { "total": 2290.866737577, "count": 1, "self": 3.903320093884304, "children": { "TrainerController._reset_env": { "total": 12.119333309000012, "count": 1, "self": 12.119333309000012 }, "TrainerController.advance": { "total": 2274.7336465171156, "count": 232551, "self": 4.182535599293715, "children": { "env_step": { "total": 1803.44666582992, "count": 232551, "self": 1512.7843473479177, "children": { "SubprocessEnvManager._take_step": { "total": 287.94116870997823, "count": 232551, "self": 15.050814695026077, "children": { "TorchPolicy.evaluate": { "total": 272.89035401495215, "count": 222894, "self": 68.64053414593042, "children": { "TorchPolicy.sample_actions": { "total": 204.24981986902174, "count": 222894, "self": 204.24981986902174 } } } } }, "workers": { "total": 2.721149772024148, "count": 232551, "self": 0.0, "children": { "worker_root": { "total": 2282.7574596501745, "count": 232551, "is_parallel": true, "self": 1043.3601787621437, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002759791000016776, "count": 1, "is_parallel": true, "self": 0.0005401520000418714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022196389999749044, "count": 2, "is_parallel": true, "self": 0.0022196389999749044 } } }, "UnityEnvironment.step": { "total": 0.029209984999965855, "count": 1, "is_parallel": true, "self": 0.0002931269999066899, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002142680000360997, "count": 1, "is_parallel": true, "self": 0.0002142680000360997 }, "communicator.exchange": { "total": 0.027978253000014774, "count": 1, "is_parallel": true, "self": 0.027978253000014774 }, "steps_from_proto": { "total": 0.0007243370000082905, "count": 1, "is_parallel": true, "self": 0.00026286299998901086, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046147400001927963, "count": 2, "is_parallel": true, "self": 0.00046147400001927963 } } } } } } }, "UnityEnvironment.step": { "total": 1239.3972808880308, "count": 232550, "is_parallel": true, "self": 35.32164912215103, "children": { "UnityEnvironment._generate_step_input": { "total": 80.45199155089995, "count": 232550, "is_parallel": true, "self": 80.45199155089995 }, "communicator.exchange": { "total": 1026.6569943330046, "count": 232550, "is_parallel": true, "self": 1026.6569943330046 }, "steps_from_proto": { "total": 96.96664588197518, "count": 232550, "is_parallel": true, "self": 42.29716926895594, "children": { "_process_rank_one_or_two_observation": { "total": 54.66947661301924, "count": 465100, "is_parallel": true, "self": 54.66947661301924 } } } } } } } } } } }, "trainer_advance": { "total": 467.10444508790187, "count": 232551, "self": 6.037892031889214, "children": { "process_trajectory": { "total": 151.6904660050119, "count": 232551, "self": 151.21929098901217, "children": { "RLTrainer._checkpoint": { "total": 0.47117501599973366, "count": 4, "self": 0.47117501599973366 } } }, "_update_policy": { "total": 309.37608705100075, "count": 97, "self": 256.4958889260061, "children": { "TorchPPOOptimizer.update": { "total": 52.88019812499465, "count": 2910, "self": 52.88019812499465 } } } } } } }, "trainer_threads": { "total": 1.2740001693600789e-06, "count": 1, "self": 1.2740001693600789e-06 }, "TrainerController._save_models": { "total": 0.11043638299997838, "count": 1, "self": 0.001989643999877444, "children": { "RLTrainer._checkpoint": { "total": 0.10844673900010093, "count": 1, "self": 0.10844673900010093 } } } } } } }