{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3996156454086304, "min": 1.3996156454086304, "max": 1.4255415201187134, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72050.8125, "min": 67838.359375, "max": 76751.8046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.81238273921201, "min": 81.2439024390244, "max": 399.23809523809524, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49469.0, "min": 48752.0, "max": 50304.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999962.0, "min": 49691.0, "max": 1999962.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999962.0, "min": 49691.0, "max": 1999962.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4476406574249268, "min": 0.010962182655930519, "max": 2.4936282634735107, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1304.592529296875, "min": 1.3702728748321533, "max": 1497.1004638671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.740880934650858, "min": 1.8288623294830322, "max": 3.946891035920098, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1993.8895381689072, "min": 228.60779118537903, "max": 2349.7688068151474, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.740880934650858, "min": 1.8288623294830322, "max": 3.946891035920098, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1993.8895381689072, "min": 228.60779118537903, "max": 2349.7688068151474, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014236334891110244, "min": 0.014236334891110244, "max": 0.019963949607821024, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04270900467333073, "min": 0.029945074364756387, "max": 0.0567522911762353, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04967647774351968, "min": 0.02393269690995415, "max": 0.06064008387426535, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14902943323055903, "min": 0.0478653938199083, "max": 0.17732888634006183, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.736098754666662e-06, "min": 3.736098754666662e-06, "max": 0.000295382476539175, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1208296263999986e-05, "min": 1.1208296263999986e-05, "max": 0.0008441890686036499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124533333333335, "min": 0.10124533333333335, "max": 0.19846082500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30373600000000006, "min": 0.20766430000000005, "max": 0.58139635, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.214213333333327e-05, "min": 7.214213333333327e-05, "max": 0.004923195167500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002164263999999998, "min": 0.0002164263999999998, "max": 0.014071677865000003, "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": "1719392488", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1719397463" }, "total": 4974.9420096310005, "count": 1, "self": 0.5914004900005239, "children": { "run_training.setup": { "total": 0.09944999500009999, "count": 1, "self": 0.09944999500009999 }, "TrainerController.start_learning": { "total": 4974.251159146, "count": 1, "self": 9.225529128877497, "children": { "TrainerController._reset_env": { "total": 4.095942093000076, "count": 1, "self": 4.095942093000076 }, "TrainerController.advance": { "total": 4960.815604030122, "count": 232556, "self": 9.661076896808481, "children": { "env_step": { "total": 3288.5336047880514, "count": 232556, "self": 2751.273179318143, "children": { "SubprocessEnvManager._take_step": { "total": 530.9636618658224, "count": 232556, "self": 37.175056820008535, "children": { "TorchPolicy.evaluate": { "total": 493.7886050458138, "count": 223074, "self": 493.7886050458138 } } }, "workers": { "total": 6.296763604086436, "count": 232556, "self": 0.0, "children": { "worker_root": { "total": 4959.574444648972, "count": 232556, "is_parallel": true, "self": 2791.9621120489996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011357559999396472, "count": 1, "is_parallel": true, "self": 0.00027229299996633927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008634629999733079, "count": 2, "is_parallel": true, "self": 0.0008634629999733079 } } }, "UnityEnvironment.step": { "total": 0.07091916699994272, "count": 1, "is_parallel": true, "self": 0.0005113009998467533, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022838900008537166, "count": 1, "is_parallel": true, "self": 0.00022838900008537166 }, "communicator.exchange": { "total": 0.06922153499999695, "count": 1, "is_parallel": true, "self": 0.06922153499999695 }, "steps_from_proto": { "total": 0.0009579420000136452, "count": 1, "is_parallel": true, "self": 0.00027216900002713373, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006857729999865114, "count": 2, "is_parallel": true, "self": 0.0006857729999865114 } } } } } } }, "UnityEnvironment.step": { "total": 2167.612332599972, "count": 232555, "is_parallel": true, "self": 69.48802638811958, "children": { "UnityEnvironment._generate_step_input": { "total": 118.40613630685164, "count": 232555, "is_parallel": true, "self": 118.40613630685164 }, "communicator.exchange": { "total": 1831.6139541620646, "count": 232555, "is_parallel": true, "self": 1831.6139541620646 }, "steps_from_proto": { "total": 148.10421574293616, "count": 232555, "is_parallel": true, "self": 46.648285507688, "children": { "_process_rank_one_or_two_observation": { "total": 101.45593023524816, "count": 465110, "is_parallel": true, "self": 101.45593023524816 } } } } } } } } } } }, "trainer_advance": { "total": 1662.620922345262, "count": 232556, "self": 15.835846590393885, "children": { "process_trajectory": { "total": 277.98614231286945, "count": 232556, "self": 276.50919325486905, "children": { "RLTrainer._checkpoint": { "total": 1.4769490580004003, "count": 10, "self": 1.4769490580004003 } } }, "_update_policy": { "total": 1368.7989334419985, "count": 97, "self": 361.5589512810204, "children": { "TorchPPOOptimizer.update": { "total": 1007.2399821609781, "count": 2910, "self": 1007.2399821609781 } } } } } } }, "trainer_threads": { "total": 1.1470001481939107e-06, "count": 1, "self": 1.1470001481939107e-06 }, "TrainerController._save_models": { "total": 0.11408274699988397, "count": 1, "self": 0.0028714979998767376, "children": { "RLTrainer._checkpoint": { "total": 0.11121124900000723, "count": 1, "self": 0.11121124900000723 } } } } } } }