{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4036800861358643, "min": 1.4036800861358643, "max": 1.4259495735168457, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70119.4375, "min": 69005.0859375, "max": 78046.0625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 73.77627627627628, "min": 70.76327116212339, "max": 414.73553719008265, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49135.0, "min": 48558.0, "max": 50183.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999930.0, "min": 49951.0, "max": 1999930.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999930.0, "min": 49951.0, "max": 1999930.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4933183193206787, "min": 0.1370192915201187, "max": 2.5214684009552, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1660.5499267578125, "min": 16.44231414794922, "max": 1660.5499267578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8783917419008307, "min": 1.8837383322417736, "max": 4.033997370337798, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2583.008900105953, "min": 226.04859986901283, "max": 2608.297647893429, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8783917419008307, "min": 1.8837383322417736, "max": 4.033997370337798, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2583.008900105953, "min": 226.04859986901283, "max": 2608.297647893429, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015955368234830933, "min": 0.014433966003444867, "max": 0.02167021375304709, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047866104704492804, "min": 0.030403109965845942, "max": 0.05879593257268425, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06389794424176215, "min": 0.021478376258164643, "max": 0.06539444724718729, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19169383272528645, "min": 0.042956752516329286, "max": 0.19469028326372306, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.973848675416664e-06, "min": 3.973848675416664e-06, "max": 0.000295347676550775, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1921546026249992e-05, "min": 1.1921546026249992e-05, "max": 0.0008443036685654499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10132458333333333, "min": 0.10132458333333333, "max": 0.198449225, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30397375, "min": 0.20777805, "max": 0.5814345500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.609670833333331e-05, "min": 7.609670833333331e-05, "max": 0.0049226163275000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022829012499999993, "min": 0.00022829012499999993, "max": 0.014073584044999999, "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": "1720775035", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720777446" }, "total": 2410.7805955540002, "count": 1, "self": 0.9387844240004597, "children": { "run_training.setup": { "total": 0.06198875699999462, "count": 1, "self": 0.06198875699999462 }, "TrainerController.start_learning": { "total": 2409.7798223729997, "count": 1, "self": 4.47403776901092, "children": { "TrainerController._reset_env": { "total": 3.1138391189999766, "count": 1, "self": 3.1138391189999766 }, "TrainerController.advance": { "total": 2402.020377614989, "count": 233164, "self": 4.7217359398555345, "children": { "env_step": { "total": 1891.2473710171287, "count": 233164, "self": 1558.6218393450938, "children": { "SubprocessEnvManager._take_step": { "total": 329.7195624820357, "count": 233164, "self": 18.11225642109497, "children": { "TorchPolicy.evaluate": { "total": 311.60730606094074, "count": 222921, "self": 311.60730606094074 } } }, "workers": { "total": 2.905969189999098, "count": 233164, "self": 0.0, "children": { "worker_root": { "total": 2402.189401151903, "count": 233164, "is_parallel": true, "self": 1156.111672393969, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008651130000316698, "count": 1, "is_parallel": true, "self": 0.0001900489999684396, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006750640000632302, "count": 2, "is_parallel": true, "self": 0.0006750640000632302 } } }, "UnityEnvironment.step": { "total": 0.02925736899999265, "count": 1, "is_parallel": true, "self": 0.00037758499996698447, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023757600001772516, "count": 1, "is_parallel": true, "self": 0.00023757600001772516 }, "communicator.exchange": { "total": 0.027884735999975874, "count": 1, "is_parallel": true, "self": 0.027884735999975874 }, "steps_from_proto": { "total": 0.0007574720000320667, "count": 1, "is_parallel": true, "self": 0.00020954899997605025, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005479230000560165, "count": 2, "is_parallel": true, "self": 0.0005479230000560165 } } } } } } }, "UnityEnvironment.step": { "total": 1246.077728757934, "count": 233163, "is_parallel": true, "self": 39.14972497477015, "children": { "UnityEnvironment._generate_step_input": { "total": 80.40329080709671, "count": 233163, "is_parallel": true, "self": 80.40329080709671 }, "communicator.exchange": { "total": 1038.011248096047, "count": 233163, "is_parallel": true, "self": 1038.011248096047 }, "steps_from_proto": { "total": 88.51346488002008, "count": 233163, "is_parallel": true, "self": 31.59260079503224, "children": { "_process_rank_one_or_two_observation": { "total": 56.92086408498784, "count": 466326, "is_parallel": true, "self": 56.92086408498784 } } } } } } } } } } }, "trainer_advance": { "total": 506.05127065800446, "count": 233164, "self": 6.778201334050607, "children": { "process_trajectory": { "total": 158.1500750989564, "count": 233164, "self": 156.49144879495594, "children": { "RLTrainer._checkpoint": { "total": 1.6586263040004496, "count": 10, "self": 1.6586263040004496 } } }, "_update_policy": { "total": 341.12299422499746, "count": 97, "self": 276.9342273139939, "children": { "TorchPPOOptimizer.update": { "total": 64.18876691100354, "count": 2910, "self": 64.18876691100354 } } } } } } }, "trainer_threads": { "total": 1.692999830993358e-06, "count": 1, "self": 1.692999830993358e-06 }, "TrainerController._save_models": { "total": 0.17156617699993149, "count": 1, "self": 0.0028596859997378488, "children": { "RLTrainer._checkpoint": { "total": 0.16870649100019364, "count": 1, "self": 0.16870649100019364 } } } } } } }