{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.411297082901001, "min": 1.411297082901001, "max": 1.4309160709381104, "count": 33 }, "Huggy.Policy.Entropy.sum": { "value": 70725.7421875, "min": 69101.515625, "max": 76711.5859375, "count": 33 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.75593220338983, "min": 83.26520270270271, "max": 402.736, "count": 33 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49416.0, "min": 49293.0, "max": 50342.0, "count": 33 }, "Huggy.Step.mean": { "value": 1649968.0, "min": 49717.0, "max": 1649968.0, "count": 33 }, "Huggy.Step.sum": { "value": 1649968.0, "min": 49717.0, "max": 1649968.0, "count": 33 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.455158233642578, "min": 0.048722367733716965, "max": 2.4814071655273438, "count": 33 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1448.5433349609375, "min": 6.041573524475098, "max": 1448.5433349609375, "count": 33 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8068177556587477, "min": 1.7828408304241397, "max": 3.9946386888623238, "count": 33 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2246.022475838661, "min": 221.0722629725933, "max": 2259.907814025879, "count": 33 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8068177556587477, "min": 1.7828408304241397, "max": 3.9946386888623238, "count": 33 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2246.022475838661, "min": 221.0722629725933, "max": 2259.907814025879, "count": 33 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01768688972709545, "min": 0.013964975702886781, "max": 0.019541622623607206, "count": 33 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05306066918128635, "min": 0.027929951405773562, "max": 0.058483869730844164, "count": 33 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.055627608920137094, "min": 0.023850350982199113, "max": 0.06080559318264325, "count": 33 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16688282676041127, "min": 0.047700701964398226, "max": 0.1774191187073787, "count": 33 }, "Huggy.Policy.LearningRate.mean": { "value": 5.5904381365233317e-05, "min": 5.5904381365233317e-05, "max": 0.0002953427265524251, "count": 33 }, "Huggy.Policy.LearningRate.sum": { "value": 0.00016771314409569994, "min": 0.00012737190754274997, "max": 0.0008440368186544, "count": 33 }, "Huggy.Policy.Epsilon.mean": { "value": 0.11863476666666666, "min": 0.11863476666666666, "max": 0.198447575, "count": 33 }, "Huggy.Policy.Epsilon.sum": { "value": 0.35590429999999995, "min": 0.24245724999999996, "max": 0.5813456000000001, "count": 33 }, "Huggy.Policy.Beta.mean": { "value": 0.0009398748566666667, "min": 0.0009398748566666667, "max": 0.004922533992500001, "count": 33 }, "Huggy.Policy.Beta.sum": { "value": 0.00281962457, "min": 0.0021386167749999994, "max": 0.014069145439999998, "count": 33 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700613070", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700615093" }, "total": 2023.903513906, "count": 1, "self": 0.27522390099989025, "children": { "run_training.setup": { "total": 0.04551751100001411, "count": 1, "self": 0.04551751100001411 }, "TrainerController.start_learning": { "total": 2023.582772494, "count": 1, "self": 3.5670877819845828, "children": { "TrainerController._reset_env": { "total": 10.365617853999964, "count": 1, "self": 10.365617853999964 }, "TrainerController.advance": { "total": 2009.4920082330157, "count": 196190, "self": 3.758568513962473, "children": { "env_step": { "total": 1584.2919518610659, "count": 196190, "self": 1305.3707429730669, "children": { "SubprocessEnvManager._take_step": { "total": 276.63594247996184, "count": 196190, "self": 14.364193088903392, "children": { "TorchPolicy.evaluate": { "total": 262.27174939105845, "count": 188301, "self": 262.27174939105845 } } }, "workers": { "total": 2.2852664080372165, "count": 196190, "self": 0.0, "children": { "worker_root": { "total": 2015.9801544589905, "count": 196190, "is_parallel": true, "self": 955.9642593700335, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008428120000019135, "count": 1, "is_parallel": true, "self": 0.00023281400001451402, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006099979999873995, "count": 2, "is_parallel": true, "self": 0.0006099979999873995 } } }, "UnityEnvironment.step": { "total": 0.03137929299998632, "count": 1, "is_parallel": true, "self": 0.0003001860000040324, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019483500000205822, "count": 1, "is_parallel": true, "self": 0.00019483500000205822 }, "communicator.exchange": { "total": 0.03016209700001582, "count": 1, "is_parallel": true, "self": 0.03016209700001582 }, "steps_from_proto": { "total": 0.0007221749999644089, "count": 1, "is_parallel": true, "self": 0.0001977499999270549, "children": { "_process_rank_one_or_two_observation": { "total": 0.000524425000037354, "count": 2, "is_parallel": true, "self": 0.000524425000037354 } } } } } } }, "UnityEnvironment.step": { "total": 1060.015895088957, "count": 196189, "is_parallel": true, "self": 33.13011727403227, "children": { "UnityEnvironment._generate_step_input": { "total": 68.5969564669814, "count": 196189, "is_parallel": true, "self": 68.5969564669814 }, "communicator.exchange": { "total": 884.5738039549715, "count": 196189, "is_parallel": true, "self": 884.5738039549715 }, "steps_from_proto": { "total": 73.7150173929719, "count": 196189, "is_parallel": true, "self": 25.879456478937584, "children": { "_process_rank_one_or_two_observation": { "total": 47.83556091403432, "count": 392378, "is_parallel": true, "self": 47.83556091403432 } } } } } } } } } } }, "trainer_advance": { "total": 421.4414878579873, "count": 196190, "self": 5.337370396001404, "children": { "process_trajectory": { "total": 127.18227678198542, "count": 196190, "self": 126.28072476298553, "children": { "RLTrainer._checkpoint": { "total": 0.9015520189998938, "count": 8, "self": 0.9015520189998938 } } }, "_update_policy": { "total": 288.92184068000046, "count": 82, "self": 236.70654740099724, "children": { "TorchPPOOptimizer.update": { "total": 52.21529327900322, "count": 2440, "self": 52.21529327900322 } } } } } } }, "trainer_threads": { "total": 1.3899998521083035e-06, "count": 1, "self": 1.3899998521083035e-06 }, "TrainerController._save_models": { "total": 0.15805723499988744, "count": 1, "self": 0.0027641539995784115, "children": { "RLTrainer._checkpoint": { "total": 0.15529308100030903, "count": 1, "self": 0.15529308100030903 } } } } } } }