{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4036386013031006, "min": 1.4036365747451782, "max": 1.424462080001831, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70076.65625, "min": 67616.421875, "max": 77650.75, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 123.8375, "min": 90.54181818181819, "max": 410.54918032786884, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49535.0, "min": 48879.0, "max": 50233.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999982.0, "min": 49752.0, "max": 1999982.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999982.0, "min": 49752.0, "max": 1999982.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2403652667999268, "min": 0.08617677539587021, "max": 2.4401042461395264, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 896.1461181640625, "min": 10.427390098571777, "max": 1287.8297119140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.2256949135661124, "min": 1.915161275174007, "max": 3.938319345480179, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1290.277965426445, "min": 231.73451429605484, "max": 2055.7411836385727, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.2256949135661124, "min": 1.915161275174007, "max": 3.938319345480179, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1290.277965426445, "min": 231.73451429605484, "max": 2055.7411836385727, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015450204984517768, "min": 0.013556333600718062, "max": 0.019715543404971766, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.030900409969035536, "min": 0.027112667201436125, "max": 0.0591466302149153, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04320297483354807, "min": 0.022319794880847135, "max": 0.06697914482404788, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08640594966709614, "min": 0.04463958976169427, "max": 0.1770000971853733, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.544723485125013e-06, "min": 4.544723485125013e-06, "max": 0.0002953755015415, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.089446970250026e-06, "min": 9.089446970250026e-06, "max": 0.0008444535185155, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10151487500000003, "min": 0.10151487500000003, "max": 0.19845850000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20302975000000006, "min": 0.20302975000000006, "max": 0.5814845000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.559226250000026e-05, "min": 8.559226250000026e-05, "max": 0.004923079150000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001711845250000005, "min": 0.0001711845250000005, "max": 0.014076076549999997, "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": "1708985761", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708988123" }, "total": 2362.0912494390004, "count": 1, "self": 0.4404037170002084, "children": { "run_training.setup": { "total": 0.057498688999999104, "count": 1, "self": 0.057498688999999104 }, "TrainerController.start_learning": { "total": 2361.593347033, "count": 1, "self": 4.401184413997726, "children": { "TrainerController._reset_env": { "total": 3.0697808200000054, "count": 1, "self": 3.0697808200000054 }, "TrainerController.advance": { "total": 2353.9955073880024, "count": 231223, "self": 4.603033375130508, "children": { "env_step": { "total": 1873.7806318119558, "count": 231223, "self": 1552.3106176248739, "children": { "SubprocessEnvManager._take_step": { "total": 318.66947946102505, "count": 231223, "self": 17.803660614016053, "children": { "TorchPolicy.evaluate": { "total": 300.865818847009, "count": 223036, "self": 300.865818847009 } } }, "workers": { "total": 2.800534726056867, "count": 231223, "self": 0.0, "children": { "worker_root": { "total": 2354.619389537992, "count": 231223, "is_parallel": true, "self": 1087.0344550150232, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011508910000657124, "count": 1, "is_parallel": true, "self": 0.0003240940000068804, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008267970000588321, "count": 2, "is_parallel": true, "self": 0.0008267970000588321 } } }, "UnityEnvironment.step": { "total": 0.03089184700002079, "count": 1, "is_parallel": true, "self": 0.00038305999999010965, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023951299999680487, "count": 1, "is_parallel": true, "self": 0.00023951299999680487 }, "communicator.exchange": { "total": 0.029097893999960434, "count": 1, "is_parallel": true, "self": 0.029097893999960434 }, "steps_from_proto": { "total": 0.001171380000073441, "count": 1, "is_parallel": true, "self": 0.0005596880000666715, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006116920000067694, "count": 2, "is_parallel": true, "self": 0.0006116920000067694 } } } } } } }, "UnityEnvironment.step": { "total": 1267.5849345229688, "count": 231222, "is_parallel": true, "self": 40.80902565001725, "children": { "UnityEnvironment._generate_step_input": { "total": 83.58953279095601, "count": 231222, "is_parallel": true, "self": 83.58953279095601 }, "communicator.exchange": { "total": 1050.641219243042, "count": 231222, "is_parallel": true, "self": 1050.641219243042 }, "steps_from_proto": { "total": 92.54515683895329, "count": 231222, "is_parallel": true, "self": 34.01012829094191, "children": { "_process_rank_one_or_two_observation": { "total": 58.53502854801138, "count": 462444, "is_parallel": true, "self": 58.53502854801138 } } } } } } } } } } }, "trainer_advance": { "total": 475.61184220091616, "count": 231223, "self": 6.382460824837494, "children": { "process_trajectory": { "total": 139.97622372507783, "count": 231223, "self": 138.72069231007765, "children": { "RLTrainer._checkpoint": { "total": 1.2555314150001777, "count": 10, "self": 1.2555314150001777 } } }, "_update_policy": { "total": 329.25315765100083, "count": 96, "self": 265.46246381900903, "children": { "TorchPPOOptimizer.update": { "total": 63.7906938319918, "count": 2880, "self": 63.7906938319918 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.12687343200013856, "count": 1, "self": 0.0029228340004010533, "children": { "RLTrainer._checkpoint": { "total": 0.12395059799973751, "count": 1, "self": 0.12395059799973751 } } } } } } }