{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4037138223648071, "min": 1.4037138223648071, "max": 1.4258427619934082, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70463.625, "min": 69625.453125, "max": 76912.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 62.9846547314578, "min": 62.9846547314578, "max": 374.1940298507463, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49254.0, "min": 48745.0, "max": 50142.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999998.0, "min": 49526.0, "max": 1999998.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999998.0, "min": 49526.0, "max": 1999998.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.502431631088257, "min": 0.16181904077529907, "max": 2.5493414402008057, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1956.9014892578125, "min": 21.52193260192871, "max": 1956.9014892578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.885496874142181, "min": 1.9308368813498575, "max": 4.059054878404301, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 3038.4585555791855, "min": 256.80130521953106, "max": 3038.4585555791855, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.885496874142181, "min": 1.9308368813498575, "max": 4.059054878404301, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 3038.4585555791855, "min": 256.80130521953106, "max": 3038.4585555791855, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017070003717445718, "min": 0.01328645814662903, "max": 0.01965780814126548, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05121001115233715, "min": 0.0276009411890603, "max": 0.05897342442379644, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06397508428328567, "min": 0.02170975993697842, "max": 0.06397508428328567, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.191925252849857, "min": 0.04341951987395684, "max": 0.191925252849857, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.816648727816662e-06, "min": 3.816648727816662e-06, "max": 0.00029537055154315, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1449946183449987e-05, "min": 1.1449946183449987e-05, "max": 0.0008441991186003, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127218333333332, "min": 0.10127218333333332, "max": 0.19845685000000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30381654999999996, "min": 0.20767405000000003, "max": 0.5813997, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.348194833333327e-05, "min": 7.348194833333327e-05, "max": 0.004922996815, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022044584499999982, "min": 0.00022044584499999982, "max": 0.01407184503, "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": "1732007016", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732009486" }, "total": 2469.969377566, "count": 1, "self": 0.60951026299972, "children": { "run_training.setup": { "total": 0.055538317000014104, "count": 1, "self": 0.055538317000014104 }, "TrainerController.start_learning": { "total": 2469.304328986, "count": 1, "self": 4.476969417005876, "children": { "TrainerController._reset_env": { "total": 4.88173860500001, "count": 1, "self": 4.88173860500001 }, "TrainerController.advance": { "total": 2459.8372442559944, "count": 234055, "self": 4.5142506399356535, "children": { "env_step": { "total": 1937.6950716240824, "count": 234055, "self": 1525.781337954209, "children": { "SubprocessEnvManager._take_step": { "total": 409.2272296129943, "count": 234055, "self": 15.64113960401437, "children": { "TorchPolicy.evaluate": { "total": 393.5860900089799, "count": 222908, "self": 393.5860900089799 } } }, "workers": { "total": 2.68650405687913, "count": 234055, "self": 0.0, "children": { "worker_root": { "total": 2461.933265101966, "count": 234055, "is_parallel": true, "self": 1217.836237864976, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009652840000171636, "count": 1, "is_parallel": true, "self": 0.00025233100006971654, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007129529999474471, "count": 2, "is_parallel": true, "self": 0.0007129529999474471 } } }, "UnityEnvironment.step": { "total": 0.029016448999982458, "count": 1, "is_parallel": true, "self": 0.00034804599988547125, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001848310000696074, "count": 1, "is_parallel": true, "self": 0.0001848310000696074 }, "communicator.exchange": { "total": 0.02772441299998718, "count": 1, "is_parallel": true, "self": 0.02772441299998718 }, "steps_from_proto": { "total": 0.0007591590000401993, "count": 1, "is_parallel": true, "self": 0.00019529400003648334, "children": { "_process_rank_one_or_two_observation": { "total": 0.000563865000003716, "count": 2, "is_parallel": true, "self": 0.000563865000003716 } } } } } } }, "UnityEnvironment.step": { "total": 1244.0970272369898, "count": 234054, "is_parallel": true, "self": 37.10610476896886, "children": { "UnityEnvironment._generate_step_input": { "total": 80.16299396300724, "count": 234054, "is_parallel": true, "self": 80.16299396300724 }, "communicator.exchange": { "total": 1037.537818605962, "count": 234054, "is_parallel": true, "self": 1037.537818605962 }, "steps_from_proto": { "total": 89.29010989905157, "count": 234054, "is_parallel": true, "self": 33.578952297046726, "children": { "_process_rank_one_or_two_observation": { "total": 55.711157602004846, "count": 468108, "is_parallel": true, "self": 55.711157602004846 } } } } } } } } } } }, "trainer_advance": { "total": 517.6279219919766, "count": 234055, "self": 6.378527524029323, "children": { "process_trajectory": { "total": 177.99200022594914, "count": 234055, "self": 176.61951276194895, "children": { "RLTrainer._checkpoint": { "total": 1.3724874640001872, "count": 10, "self": 1.3724874640001872 } } }, "_update_policy": { "total": 333.2573942419981, "count": 97, "self": 268.138748402003, "children": { "TorchPPOOptimizer.update": { "total": 65.11864583999511, "count": 2910, "self": 65.11864583999511 } } } } } } }, "trainer_threads": { "total": 1.3049998415226582e-06, "count": 1, "self": 1.3049998415226582e-06 }, "TrainerController._save_models": { "total": 0.10837540300008186, "count": 1, "self": 0.001972357999875385, "children": { "RLTrainer._checkpoint": { "total": 0.10640304500020648, "count": 1, "self": 0.10640304500020648 } } } } } } }