{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4065760374069214, "min": 1.4065760374069214, "max": 1.428511142730713, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71147.4296875, "min": 69028.921875, "max": 77202.765625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.0867924528302, "min": 73.90419161676647, "max": 395.984126984127, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48806.0, "min": 48806.0, "max": 50111.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999961.0, "min": 49270.0, "max": 1999961.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999961.0, "min": 49270.0, "max": 1999961.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4375555515289307, "min": 0.09388220310211182, "max": 2.483473300933838, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1291.9044189453125, "min": 11.735275268554688, "max": 1600.18994140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7814017796291495, "min": 1.7683164225816728, "max": 3.9941716484255174, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2004.1429432034492, "min": 221.03955282270908, "max": 2479.044963002205, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7814017796291495, "min": 1.7683164225816728, "max": 3.9941716484255174, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2004.1429432034492, "min": 221.03955282270908, "max": 2479.044963002205, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018248013691562745, "min": 0.013711116932669635, "max": 0.022420570952817798, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.054744041074688235, "min": 0.02742223386533927, "max": 0.06414937443235734, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.048517807407511604, "min": 0.021804422854135433, "max": 0.06086087574561437, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1455534222225348, "min": 0.043608845708270866, "max": 0.1825201090425253, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.531598822833344e-06, "min": 3.531598822833344e-06, "max": 0.00029537647654117493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0594796468500032e-05, "min": 1.0594796468500032e-05, "max": 0.0008440555686481499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117716666666669, "min": 0.10117716666666669, "max": 0.198458825, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30353150000000007, "min": 0.2075393, "max": 0.58135185, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.874061666666682e-05, "min": 6.874061666666682e-05, "max": 0.0049230953675, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020622185000000046, "min": 0.00020622185000000046, "max": 0.014069457314999999, "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": "1722822258", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722826613" }, "total": 4354.473612222, "count": 1, "self": 0.8594241069995405, "children": { "run_training.setup": { "total": 0.07628237900007662, "count": 1, "self": 0.07628237900007662 }, "TrainerController.start_learning": { "total": 4353.5379057360005, "count": 1, "self": 7.5291313938068924, "children": { "TrainerController._reset_env": { "total": 3.6978101610000067, "count": 1, "self": 3.6978101610000067 }, "TrainerController.advance": { "total": 4342.164813691193, "count": 233245, "self": 8.071735377140612, "children": { "env_step": { "total": 2797.072742511087, "count": 233245, "self": 2348.3644894478844, "children": { "SubprocessEnvManager._take_step": { "total": 443.5528334081024, "count": 233245, "self": 28.498919020094718, "children": { "TorchPolicy.evaluate": { "total": 415.0539143880077, "count": 223102, "self": 415.0539143880077 } } }, "workers": { "total": 5.155419655100445, "count": 233245, "self": 0.0, "children": { "worker_root": { "total": 4340.55038467896, "count": 233245, "is_parallel": true, "self": 2482.210087254043, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009973429999945438, "count": 1, "is_parallel": true, "self": 0.0002543230000355834, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007430199999589604, "count": 2, "is_parallel": true, "self": 0.0007430199999589604 } } }, "UnityEnvironment.step": { "total": 0.05446826299998975, "count": 1, "is_parallel": true, "self": 0.00042178399996828375, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000201231000005464, "count": 1, "is_parallel": true, "self": 0.000201231000005464 }, "communicator.exchange": { "total": 0.05300433399997928, "count": 1, "is_parallel": true, "self": 0.05300433399997928 }, "steps_from_proto": { "total": 0.0008409140000367188, "count": 1, "is_parallel": true, "self": 0.00022744299997157214, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006134710000651467, "count": 2, "is_parallel": true, "self": 0.0006134710000651467 } } } } } } }, "UnityEnvironment.step": { "total": 1858.3402974249168, "count": 233244, "is_parallel": true, "self": 59.78132670580612, "children": { "UnityEnvironment._generate_step_input": { "total": 105.87364292700363, "count": 233244, "is_parallel": true, "self": 105.87364292700363 }, "communicator.exchange": { "total": 1559.8961288641165, "count": 233244, "is_parallel": true, "self": 1559.8961288641165 }, "steps_from_proto": { "total": 132.78919892799047, "count": 233244, "is_parallel": true, "self": 43.25368482229237, "children": { "_process_rank_one_or_two_observation": { "total": 89.5355141056981, "count": 466488, "is_parallel": true, "self": 89.5355141056981 } } } } } } } } } } }, "trainer_advance": { "total": 1537.0203358029646, "count": 233245, "self": 12.012931510013914, "children": { "process_trajectory": { "total": 243.24202211395027, "count": 233245, "self": 241.88630355895089, "children": { "RLTrainer._checkpoint": { "total": 1.3557185549993847, "count": 10, "self": 1.3557185549993847 } } }, "_update_policy": { "total": 1281.7653821790004, "count": 97, "self": 332.48670919500364, "children": { "TorchPPOOptimizer.update": { "total": 949.2786729839968, "count": 2910, "self": 949.2786729839968 } } } } } } }, "trainer_threads": { "total": 1.4080005712457933e-06, "count": 1, "self": 1.4080005712457933e-06 }, "TrainerController._save_models": { "total": 0.14614908200019272, "count": 1, "self": 0.0030084150002949173, "children": { "RLTrainer._checkpoint": { "total": 0.1431406669998978, "count": 1, "self": 0.1431406669998978 } } } } } } }