{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3946245908737183, "min": 1.3946245908737183, "max": 1.4272160530090332, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70986.390625, "min": 68630.1953125, "max": 75009.6796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.8132854578097, "min": 74.65204236006052, "max": 393.6456692913386, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49469.0, "min": 49091.0, "max": 50163.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999971.0, "min": 49683.0, "max": 1999971.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999971.0, "min": 49683.0, "max": 1999971.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3848414421081543, "min": -0.0825207307934761, "max": 2.496386766433716, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1328.356689453125, "min": -10.397611618041992, "max": 1614.7672119140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.70851296871312, "min": 1.6844967611961894, "max": 4.029623847801003, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2065.641723573208, "min": 212.24659191071987, "max": 2537.0808581113815, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.70851296871312, "min": 1.6844967611961894, "max": 4.029623847801003, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2065.641723573208, "min": 212.24659191071987, "max": 2537.0808581113815, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0153306315064482, "min": 0.012434702702254677, "max": 0.02031152491690591, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0459918945193446, "min": 0.02561301766060448, "max": 0.05578539147779035, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.059880147253473605, "min": 0.024836418249954778, "max": 0.06411732025444508, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17964044176042082, "min": 0.049672836499909556, "max": 0.18555009774863723, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.498098834000001e-06, "min": 3.498098834000001e-06, "max": 0.0002952519015827, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0494296502000003e-05, "min": 1.0494296502000003e-05, "max": 0.0008438802187065999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116599999999999, "min": 0.10116599999999999, "max": 0.19841730000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.303498, "min": 0.20745684999999997, "max": 0.5812934000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.818340000000002e-05, "min": 6.818340000000002e-05, "max": 0.004921023270000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020455020000000008, "min": 0.00020455020000000008, "max": 0.014066540660000001, "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": "1710335471", "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_sagravela --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": "1710337925" }, "total": 2454.741572677, "count": 1, "self": 0.4387148780001553, "children": { "run_training.setup": { "total": 0.054866076000053, "count": 1, "self": 0.054866076000053 }, "TrainerController.start_learning": { "total": 2454.247991723, "count": 1, "self": 4.493440564955108, "children": { "TrainerController._reset_env": { "total": 3.3567540899999813, "count": 1, "self": 3.3567540899999813 }, "TrainerController.advance": { "total": 2446.220677658045, "count": 232980, "self": 4.666751900936106, "children": { "env_step": { "total": 1962.2119488521262, "count": 232980, "self": 1627.112606564197, "children": { "SubprocessEnvManager._take_step": { "total": 332.2173069679268, "count": 232980, "self": 17.294749833930382, "children": { "TorchPolicy.evaluate": { "total": 314.9225571339964, "count": 223046, "self": 314.9225571339964 } } }, "workers": { "total": 2.8820353200022737, "count": 232980, "self": 0.0, "children": { "worker_root": { "total": 2447.0392060150393, "count": 232980, "is_parallel": true, "self": 1123.5293033690555, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009540229999629446, "count": 1, "is_parallel": true, "self": 0.00020707900000616064, "children": { "_process_rank_one_or_two_observation": { "total": 0.000746943999956784, "count": 2, "is_parallel": true, "self": 0.000746943999956784 } } }, "UnityEnvironment.step": { "total": 0.0302295269999604, "count": 1, "is_parallel": true, "self": 0.00038409399985539494, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002273470000773159, "count": 1, "is_parallel": true, "self": 0.0002273470000773159 }, "communicator.exchange": { "total": 0.028876259000071514, "count": 1, "is_parallel": true, "self": 0.028876259000071514 }, "steps_from_proto": { "total": 0.0007418269999561744, "count": 1, "is_parallel": true, "self": 0.00019969200002378784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005421349999323866, "count": 2, "is_parallel": true, "self": 0.0005421349999323866 } } } } } } }, "UnityEnvironment.step": { "total": 1323.5099026459839, "count": 232979, "is_parallel": true, "self": 40.0537911780184, "children": { "UnityEnvironment._generate_step_input": { "total": 82.06452414507226, "count": 232979, "is_parallel": true, "self": 82.06452414507226 }, "communicator.exchange": { "total": 1108.5776774359852, "count": 232979, "is_parallel": true, "self": 1108.5776774359852 }, "steps_from_proto": { "total": 92.81390988690794, "count": 232979, "is_parallel": true, "self": 33.26857278508544, "children": { "_process_rank_one_or_two_observation": { "total": 59.5453371018225, "count": 465958, "is_parallel": true, "self": 59.5453371018225 } } } } } } } } } } }, "trainer_advance": { "total": 479.3419769049831, "count": 232980, "self": 6.9152286620361565, "children": { "process_trajectory": { "total": 159.36353522794786, "count": 232980, "self": 157.91504044794806, "children": { "RLTrainer._checkpoint": { "total": 1.4484947799998054, "count": 10, "self": 1.4484947799998054 } } }, "_update_policy": { "total": 313.06321301499906, "count": 97, "self": 250.0406551410083, "children": { "TorchPPOOptimizer.update": { "total": 63.02255787399076, "count": 2910, "self": 63.02255787399076 } } } } } } }, "trainer_threads": { "total": 1.5339996934926603e-06, "count": 1, "self": 1.5339996934926603e-06 }, "TrainerController._save_models": { "total": 0.17711787600001117, "count": 1, "self": 0.0020907439998154587, "children": { "RLTrainer._checkpoint": { "total": 0.1750271320001957, "count": 1, "self": 0.1750271320001957 } } } } } } }