{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4064042568206787, "min": 1.4064042568206787, "max": 1.4282565116882324, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70448.1953125, "min": 67833.8046875, "max": 78051.859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.67603305785124, "min": 79.71451612903226, "max": 406.23387096774195, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49414.0, "min": 49139.0, "max": 50373.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999976.0, "min": 49976.0, "max": 1999976.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999976.0, "min": 49976.0, "max": 1999976.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4459636211395264, "min": 0.11444830149412155, "max": 2.4833924770355225, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1477.362060546875, "min": 14.077140808105469, "max": 1510.42919921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8491487786272502, "min": 1.6974167499115798, "max": 3.907226406511256, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2324.885862290859, "min": 208.7822602391243, "max": 2345.37791877985, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8491487786272502, "min": 1.6974167499115798, "max": 3.907226406511256, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2324.885862290859, "min": 208.7822602391243, "max": 2345.37791877985, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016085346967318198, "min": 0.013676492079846664, "max": 0.021147627305860322, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048256040901954594, "min": 0.027719821719938406, "max": 0.0551374361627192, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05497206855151388, "min": 0.020868296083062884, "max": 0.06323077399283647, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16491620565454165, "min": 0.04173659216612577, "max": 0.18405136118332543, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3911488696499955e-06, "min": 3.3911488696499955e-06, "max": 0.0002952663015778999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0173446608949986e-05, "min": 1.0173446608949986e-05, "max": 0.0008437074187642, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113034999999998, "min": 0.10113034999999998, "max": 0.19842210000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30339104999999994, "min": 0.20739554999999998, "max": 0.5812358000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.640446499999994e-05, "min": 6.640446499999994e-05, "max": 0.00492126279, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001992133949999998, "min": 0.0001992133949999998, "max": 0.014063666420000002, "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": "1697624900", "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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697627232" }, "total": 2332.009315451, "count": 1, "self": 0.4747297359995173, "children": { "run_training.setup": { "total": 0.07558924599993588, "count": 1, "self": 0.07558924599993588 }, "TrainerController.start_learning": { "total": 2331.4589964690003, "count": 1, "self": 4.317350138887377, "children": { "TrainerController._reset_env": { "total": 7.476960468000016, "count": 1, "self": 7.476960468000016 }, "TrainerController.advance": { "total": 2319.567312386113, "count": 232743, "self": 4.526778475272295, "children": { "env_step": { "total": 1832.7466217339856, "count": 232743, "self": 1521.6692145430036, "children": { "SubprocessEnvManager._take_step": { "total": 308.35816218198806, "count": 232743, "self": 16.61502481698176, "children": { "TorchPolicy.evaluate": { "total": 291.7431373650063, "count": 222968, "self": 291.7431373650063 } } }, "workers": { "total": 2.719245008993994, "count": 232743, "self": 0.0, "children": { "worker_root": { "total": 2323.8541399751048, "count": 232743, "is_parallel": true, "self": 1084.5063366601585, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010919219998868357, "count": 1, "is_parallel": true, "self": 0.0003473199997188203, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007446020001680154, "count": 2, "is_parallel": true, "self": 0.0007446020001680154 } } }, "UnityEnvironment.step": { "total": 0.0332289259999925, "count": 1, "is_parallel": true, "self": 0.000434021000046414, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019991299996036105, "count": 1, "is_parallel": true, "self": 0.00019991299996036105 }, "communicator.exchange": { "total": 0.03172450600004595, "count": 1, "is_parallel": true, "self": 0.03172450600004595 }, "steps_from_proto": { "total": 0.000870485999939774, "count": 1, "is_parallel": true, "self": 0.00025350700002491067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006169789999148634, "count": 2, "is_parallel": true, "self": 0.0006169789999148634 } } } } } } }, "UnityEnvironment.step": { "total": 1239.3478033149463, "count": 232742, "is_parallel": true, "self": 39.56001671302374, "children": { "UnityEnvironment._generate_step_input": { "total": 82.72494057188874, "count": 232742, "is_parallel": true, "self": 82.72494057188874 }, "communicator.exchange": { "total": 1029.3017465099304, "count": 232742, "is_parallel": true, "self": 1029.3017465099304 }, "steps_from_proto": { "total": 87.76109952010347, "count": 232742, "is_parallel": true, "self": 31.29990408710796, "children": { "_process_rank_one_or_two_observation": { "total": 56.46119543299551, "count": 465484, "is_parallel": true, "self": 56.46119543299551 } } } } } } } } } } }, "trainer_advance": { "total": 482.293912176855, "count": 232743, "self": 6.067996000820585, "children": { "process_trajectory": { "total": 144.71385713103473, "count": 232743, "self": 143.6188092620339, "children": { "RLTrainer._checkpoint": { "total": 1.0950478690008367, "count": 10, "self": 1.0950478690008367 } } }, "_update_policy": { "total": 331.51205904499966, "count": 97, "self": 270.188778768995, "children": { "TorchPPOOptimizer.update": { "total": 61.32328027600465, "count": 2910, "self": 61.32328027600465 } } } } } } }, "trainer_threads": { "total": 1.0680000741558615e-06, "count": 1, "self": 1.0680000741558615e-06 }, "TrainerController._save_models": { "total": 0.09737240799995561, "count": 1, "self": 0.0018033740002465493, "children": { "RLTrainer._checkpoint": { "total": 0.09556903399970906, "count": 1, "self": 0.09556903399970906 } } } } } } }