{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4010589122772217, "min": 1.4010589122772217, "max": 1.4267345666885376, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71068.7109375, "min": 67845.2734375, "max": 76356.046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 121.29095354523227, "min": 96.91568627450981, "max": 411.8688524590164, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49608.0, "min": 48778.0, "max": 50280.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999940.0, "min": 49837.0, "max": 1999940.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999940.0, "min": 49837.0, "max": 1999940.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.302700996398926, "min": 0.07050970196723938, "max": 2.38742733001709, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 941.8046875, "min": 8.5316743850708, "max": 1217.587890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5534780873646072, "min": 1.7215580677936886, "max": 3.911892632360128, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1453.3725377321243, "min": 208.3085262030363, "max": 1953.3719981312752, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5534780873646072, "min": 1.7215580677936886, "max": 3.911892632360128, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1453.3725377321243, "min": 208.3085262030363, "max": 1953.3719981312752, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0165600149188928, "min": 0.013280257597216405, "max": 0.01915088153206549, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0331200298377856, "min": 0.02656051519443281, "max": 0.057277931529097256, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.041060531201461956, "min": 0.02339488991225759, "max": 0.06022097201397022, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08212106240292391, "min": 0.04678977982451518, "max": 0.16398235335946082, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.391498536199995e-06, "min": 4.391498536199995e-06, "max": 0.00029535990154669995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.78299707239999e-06, "min": 8.78299707239999e-06, "max": 0.00084392476869175, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10146379999999998, "min": 0.10146379999999998, "max": 0.19845330000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20292759999999996, "min": 0.20292759999999996, "max": 0.5813082500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.304361999999992e-05, "min": 8.304361999999992e-05, "max": 0.00492281967, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016608723999999984, "min": 0.00016608723999999984, "max": 0.014067281674999998, "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": "1701523434", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701525931" }, "total": 2496.290088635, "count": 1, "self": 0.43891618300040136, "children": { "run_training.setup": { "total": 0.05701187399995433, "count": 1, "self": 0.05701187399995433 }, "TrainerController.start_learning": { "total": 2495.7941605779997, "count": 1, "self": 4.548673113072255, "children": { "TrainerController._reset_env": { "total": 3.425366877999977, "count": 1, "self": 3.425366877999977 }, "TrainerController.advance": { "total": 2487.7124197309276, "count": 231036, "self": 4.907956876950266, "children": { "env_step": { "total": 1981.4173416369629, "count": 231036, "self": 1633.3839323717823, "children": { "SubprocessEnvManager._take_step": { "total": 345.04871348717506, "count": 231036, "self": 17.54116755318273, "children": { "TorchPolicy.evaluate": { "total": 327.50754593399233, "count": 223088, "self": 327.50754593399233 } } }, "workers": { "total": 2.9846957780055163, "count": 231036, "self": 0.0, "children": { "worker_root": { "total": 2487.8946224801093, "count": 231036, "is_parallel": true, "self": 1165.26188780206, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008658740000555554, "count": 1, "is_parallel": true, "self": 0.00024577099998168705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006201030000738683, "count": 2, "is_parallel": true, "self": 0.0006201030000738683 } } }, "UnityEnvironment.step": { "total": 0.036236438999821985, "count": 1, "is_parallel": true, "self": 0.00035200699994675233, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002492979999715317, "count": 1, "is_parallel": true, "self": 0.0002492979999715317 }, "communicator.exchange": { "total": 0.03482742500000313, "count": 1, "is_parallel": true, "self": 0.03482742500000313 }, "steps_from_proto": { "total": 0.0008077089999005693, "count": 1, "is_parallel": true, "self": 0.00023410199992213165, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005736069999784377, "count": 2, "is_parallel": true, "self": 0.0005736069999784377 } } } } } } }, "UnityEnvironment.step": { "total": 1322.6327346780492, "count": 231035, "is_parallel": true, "self": 40.94090582126182, "children": { "UnityEnvironment._generate_step_input": { "total": 86.8904919998613, "count": 231035, "is_parallel": true, "self": 86.8904919998613 }, "communicator.exchange": { "total": 1101.9217068490766, "count": 231035, "is_parallel": true, "self": 1101.9217068490766 }, "steps_from_proto": { "total": 92.87963000784953, "count": 231035, "is_parallel": true, "self": 34.547525383835136, "children": { "_process_rank_one_or_two_observation": { "total": 58.33210462401439, "count": 462070, "is_parallel": true, "self": 58.33210462401439 } } } } } } } } } } }, "trainer_advance": { "total": 501.3871212170145, "count": 231036, "self": 7.300141522996682, "children": { "process_trajectory": { "total": 153.6375403650195, "count": 231036, "self": 152.4964918570197, "children": { "RLTrainer._checkpoint": { "total": 1.1410485079998125, "count": 10, "self": 1.1410485079998125 } } }, "_update_policy": { "total": 340.4494393289983, "count": 96, "self": 276.43897864800556, "children": { "TorchPPOOptimizer.update": { "total": 64.01046068099276, "count": 2880, "self": 64.01046068099276 } } } } } } }, "trainer_threads": { "total": 9.899999895424116e-07, "count": 1, "self": 9.899999895424116e-07 }, "TrainerController._save_models": { "total": 0.10769986599962067, "count": 1, "self": 0.0016884969995771826, "children": { "RLTrainer._checkpoint": { "total": 0.10601136900004349, "count": 1, "self": 0.10601136900004349 } } } } } } }