{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.401881217956543, "min": 1.401881217956543, "max": 1.42771577835083, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70921.171875, "min": 68866.25, "max": 76196.4609375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.0275387263339, "min": 85.0275387263339, "max": 379.3787878787879, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49401.0, "min": 48897.0, "max": 50078.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999930.0, "min": 49821.0, "max": 1999930.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999930.0, "min": 49821.0, "max": 1999930.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3868558406829834, "min": 0.06414066255092621, "max": 2.4403603076934814, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1386.76318359375, "min": 8.402426719665527, "max": 1391.0601806640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7112780512918087, "min": 1.9218266865679325, "max": 3.973696554079652, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2156.252547800541, "min": 251.75929594039917, "max": 2193.5096665024757, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7112780512918087, "min": 1.9218266865679325, "max": 3.973696554079652, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2156.252547800541, "min": 251.75929594039917, "max": 2193.5096665024757, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016943489796701922, "min": 0.013059693148776811, "max": 0.02025049512158148, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05083046939010577, "min": 0.026119386297553622, "max": 0.058317603364897275, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05704216373463472, "min": 0.023079156130552295, "max": 0.06155084539204836, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17112649120390416, "min": 0.04615831226110459, "max": 0.17112649120390416, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.13634895458334e-06, "min": 3.13634895458334e-06, "max": 0.0002953209015596999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.40904686375002e-06, "min": 9.40904686375002e-06, "max": 0.0008438941687019499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10104541666666668, "min": 0.10104541666666668, "max": 0.19844030000000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30313625000000005, "min": 0.20726649999999996, "max": 0.5812980499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.21662916666668e-05, "min": 6.21662916666668e-05, "max": 0.0049221709700000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018649887500000038, "min": 0.00018649887500000038, "max": 0.014066772695, "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": "1703043558", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703046003" }, "total": 2445.119967494, "count": 1, "self": 0.804115075000027, "children": { "run_training.setup": { "total": 0.0864415610000151, "count": 1, "self": 0.0864415610000151 }, "TrainerController.start_learning": { "total": 2444.229410858, "count": 1, "self": 4.575526801989781, "children": { "TrainerController._reset_env": { "total": 3.766627956000036, "count": 1, "self": 3.766627956000036 }, "TrainerController.advance": { "total": 2435.71500823601, "count": 232194, "self": 4.640779614113399, "children": { "env_step": { "total": 1936.3898677299635, "count": 232194, "self": 1607.2083559750813, "children": { "SubprocessEnvManager._take_step": { "total": 326.3675417420018, "count": 232194, "self": 17.41110069008556, "children": { "TorchPolicy.evaluate": { "total": 308.9564410519162, "count": 222960, "self": 308.9564410519162 } } }, "workers": { "total": 2.813970012880361, "count": 232194, "self": 0.0, "children": { "worker_root": { "total": 2436.99417645911, "count": 232194, "is_parallel": true, "self": 1129.4306507220663, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007609770000271965, "count": 1, "is_parallel": true, "self": 0.00021077700000660116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005502000000205953, "count": 2, "is_parallel": true, "self": 0.0005502000000205953 } } }, "UnityEnvironment.step": { "total": 0.034259267999971144, "count": 1, "is_parallel": true, "self": 0.00034202999995613936, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022137399997745888, "count": 1, "is_parallel": true, "self": 0.00022137399997745888 }, "communicator.exchange": { "total": 0.03290538600003856, "count": 1, "is_parallel": true, "self": 0.03290538600003856 }, "steps_from_proto": { "total": 0.0007904779999989842, "count": 1, "is_parallel": true, "self": 0.00022940500002732733, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005610729999716568, "count": 2, "is_parallel": true, "self": 0.0005610729999716568 } } } } } } }, "UnityEnvironment.step": { "total": 1307.5635257370436, "count": 232193, "is_parallel": true, "self": 40.702045889147485, "children": { "UnityEnvironment._generate_step_input": { "total": 81.53005136694134, "count": 232193, "is_parallel": true, "self": 81.53005136694134 }, "communicator.exchange": { "total": 1095.2364374580075, "count": 232193, "is_parallel": true, "self": 1095.2364374580075 }, "steps_from_proto": { "total": 90.09499102294745, "count": 232193, "is_parallel": true, "self": 31.223315754946498, "children": { "_process_rank_one_or_two_observation": { "total": 58.871675268000956, "count": 464386, "is_parallel": true, "self": 58.871675268000956 } } } } } } } } } } }, "trainer_advance": { "total": 494.6843608919332, "count": 232194, "self": 6.709476312998561, "children": { "process_trajectory": { "total": 154.76225512693412, "count": 232194, "self": 153.50295426393456, "children": { "RLTrainer._checkpoint": { "total": 1.2593008629995666, "count": 10, "self": 1.2593008629995666 } } }, "_update_policy": { "total": 333.2126294520005, "count": 97, "self": 267.96106044401216, "children": { "TorchPPOOptimizer.update": { "total": 65.25156900798834, "count": 2910, "self": 65.25156900798834 } } } } } } }, "trainer_threads": { "total": 1.1440001799201127e-06, "count": 1, "self": 1.1440001799201127e-06 }, "TrainerController._save_models": { "total": 0.1722467200002029, "count": 1, "self": 0.003011644000253, "children": { "RLTrainer._checkpoint": { "total": 0.1692350759999499, "count": 1, "self": 0.1692350759999499 } } } } } } }