{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403850793838501, "min": 1.403850793838501, "max": 1.4260669946670532, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69960.90625, "min": 68635.4296875, "max": 77235.03125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.02342342342342, "min": 84.18568994889267, "max": 439.05263157894734, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48853.0, "min": 48853.0, "max": 50067.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49636.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49636.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4223341941833496, "min": 0.1187036782503128, "max": 2.4705123901367188, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1344.3955078125, "min": 13.4135160446167, "max": 1422.406494140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.781817334192293, "min": 1.717575112539055, "max": 3.9754841456643675, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2098.9086204767227, "min": 194.08598771691322, "max": 2296.6863621473312, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.781817334192293, "min": 1.717575112539055, "max": 3.9754841456643675, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2098.9086204767227, "min": 194.08598771691322, "max": 2296.6863621473312, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013424600212500892, "min": 0.01232621291662023, "max": 0.020362531314215934, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.040273800637502674, "min": 0.02465242583324046, "max": 0.058705528099865956, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05431393318706088, "min": 0.020075671592106423, "max": 0.06153750972201427, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16294179956118265, "min": 0.040151343184212845, "max": 0.1793016252418359, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7302487566166655e-06, "min": 3.7302487566166655e-06, "max": 0.0002953221015592999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1190746269849996e-05, "min": 1.1190746269849996e-05, "max": 0.0008441919186027, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124338333333334, "min": 0.10124338333333334, "max": 0.19844069999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30373015000000003, "min": 0.20761565000000004, "max": 0.5813973, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.204482833333334e-05, "min": 7.204482833333334e-05, "max": 0.0049221909300000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021613448500000003, "min": 0.00021613448500000003, "max": 0.014071725270000003, "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": "1703488851", "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": "1703491386" }, "total": 2535.268699032, "count": 1, "self": 0.44502835999992385, "children": { "run_training.setup": { "total": 0.05021346399985305, "count": 1, "self": 0.05021346399985305 }, "TrainerController.start_learning": { "total": 2534.773457208, "count": 1, "self": 4.697755791990858, "children": { "TrainerController._reset_env": { "total": 2.9592867750000096, "count": 1, "self": 2.9592867750000096 }, "TrainerController.advance": { "total": 2527.001262743009, "count": 232393, "self": 4.9598369110676686, "children": { "env_step": { "total": 2014.249418511893, "count": 232393, "self": 1675.0925716259942, "children": { "SubprocessEnvManager._take_step": { "total": 336.0631884140357, "count": 232393, "self": 17.650230979057824, "children": { "TorchPolicy.evaluate": { "total": 318.4129574349779, "count": 222930, "self": 318.4129574349779 } } }, "workers": { "total": 3.0936584718631366, "count": 232393, "self": 0.0, "children": { "worker_root": { "total": 2527.3243076969184, "count": 232393, "is_parallel": true, "self": 1164.8520334089667, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006878149999920424, "count": 1, "is_parallel": true, "self": 0.00023957299981702818, "children": { "_process_rank_one_or_two_observation": { "total": 0.00044824200017501425, "count": 2, "is_parallel": true, "self": 0.00044824200017501425 } } }, "UnityEnvironment.step": { "total": 0.03190428800007794, "count": 1, "is_parallel": true, "self": 0.0003541349999522936, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021574700008386571, "count": 1, "is_parallel": true, "self": 0.00021574700008386571 }, "communicator.exchange": { "total": 0.030534230000057505, "count": 1, "is_parallel": true, "self": 0.030534230000057505 }, "steps_from_proto": { "total": 0.0008001759999842761, "count": 1, "is_parallel": true, "self": 0.00024389299983340607, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005562830001508701, "count": 2, "is_parallel": true, "self": 0.0005562830001508701 } } } } } } }, "UnityEnvironment.step": { "total": 1362.4722742879517, "count": 232392, "is_parallel": true, "self": 42.37155205976023, "children": { "UnityEnvironment._generate_step_input": { "total": 88.01070509400347, "count": 232392, "is_parallel": true, "self": 88.01070509400347 }, "communicator.exchange": { "total": 1137.2732021331701, "count": 232392, "is_parallel": true, "self": 1137.2732021331701 }, "steps_from_proto": { "total": 94.81681500101786, "count": 232392, "is_parallel": true, "self": 35.038486942000645, "children": { "_process_rank_one_or_two_observation": { "total": 59.77832805901721, "count": 464784, "is_parallel": true, "self": 59.77832805901721 } } } } } } } } } } }, "trainer_advance": { "total": 507.79200732004847, "count": 232393, "self": 6.8721569411113705, "children": { "process_trajectory": { "total": 158.9335277819407, "count": 232393, "self": 157.65772033194003, "children": { "RLTrainer._checkpoint": { "total": 1.2758074500006842, "count": 10, "self": 1.2758074500006842 } } }, "_update_policy": { "total": 341.9863225969964, "count": 97, "self": 276.98756692199845, "children": { "TorchPPOOptimizer.update": { "total": 64.99875567499794, "count": 2910, "self": 64.99875567499794 } } } } } } }, "trainer_threads": { "total": 1.041999894368928e-06, "count": 1, "self": 1.041999894368928e-06 }, "TrainerController._save_models": { "total": 0.11515085599967279, "count": 1, "self": 0.00204779099976804, "children": { "RLTrainer._checkpoint": { "total": 0.11310306499990475, "count": 1, "self": 0.11310306499990475 } } } } } } }