{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4075756072998047, "min": 1.407575249671936, "max": 1.4274826049804688, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69068.328125, "min": 68169.1640625, "max": 76799.03125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.04864864864865, "min": 78.89616613418531, "max": 410.44262295081967, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49422.0, "min": 48810.0, "max": 50106.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999946.0, "min": 49473.0, "max": 1999946.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999946.0, "min": 49473.0, "max": 1999946.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.442521095275879, "min": 0.14300185441970825, "max": 2.490424871444702, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1355.5992431640625, "min": 17.303224563598633, "max": 1495.67431640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7817151755899996, "min": 1.8541189272049046, "max": 3.996439774371551, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2098.85192245245, "min": 224.34839019179344, "max": 2396.9645188450813, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7817151755899996, "min": 1.8541189272049046, "max": 3.996439774371551, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2098.85192245245, "min": 224.34839019179344, "max": 2396.9645188450813, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016941287624002953, "min": 0.013992135474109092, "max": 0.02067528324259911, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05082386287200886, "min": 0.027984270948218183, "max": 0.05684448456995596, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05750653478834364, "min": 0.021295824367552996, "max": 0.06063232736455069, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17251960436503092, "min": 0.04259164873510599, "max": 0.18189698209365207, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8373987209e-06, "min": 3.8373987209e-06, "max": 0.00029535517654827494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.15121961627e-05, "min": 1.15121961627e-05, "max": 0.0008442951185682998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127910000000001, "min": 0.10127910000000001, "max": 0.198451725, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30383730000000003, "min": 0.20773320000000006, "max": 0.5814317000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.382708999999998e-05, "min": 7.382708999999998e-05, "max": 0.004922741077500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022148126999999994, "min": 0.00022148126999999994, "max": 0.014073441829999998, "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": "1725301094", "python_version": "3.10.14 (main, Apr 17 2024, 00:00:00) [GCC 13.2.1 20240316 (Red Hat 13.2.1-7)]", "command_line_arguments": "/home/michael/Repo/DeepRLCourse/venv/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": "2.4.0+rocm6.1", "numpy_version": "1.23.5", "end_time_seconds": "1725302155" }, "total": 1061.664441926987, "count": 1, "self": 0.21783175598829985, "children": { "run_training.setup": { "total": 0.01599983498454094, "count": 1, "self": 0.01599983498454094 }, "TrainerController.start_learning": { "total": 1061.430610336014, "count": 1, "self": 2.1581641295924783, "children": { "TrainerController._reset_env": { "total": 1.02016666601412, "count": 1, "self": 1.02016666601412 }, "TrainerController.advance": { "total": 1058.193676455412, "count": 232555, "self": 2.2503938080044463, "children": { "env_step": { "total": 805.4327636840753, "count": 232555, "self": 567.9287272152724, "children": { "SubprocessEnvManager._take_step": { "total": 236.07479570561554, "count": 232555, "self": 6.831659905496053, "children": { "TorchPolicy.evaluate": { "total": 229.2431358001195, "count": 222922, "self": 229.2431358001195 } } }, "workers": { "total": 1.4292407631874084, "count": 232555, "self": 0.0, "children": { "worker_root": { "total": 1058.4925077254884, "count": 232555, "is_parallel": true, "self": 611.9555793257896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0005044919671490788, "count": 1, "is_parallel": true, "self": 0.0001255548559129238, "children": { "_process_rank_one_or_two_observation": { "total": 0.00037893711123615503, "count": 2, "is_parallel": true, "self": 0.00037893711123615503 } } }, "UnityEnvironment.step": { "total": 0.011290291091427207, "count": 1, "is_parallel": true, "self": 0.00012192514259368181, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00012976606376469135, "count": 1, "is_parallel": true, "self": 0.00012976606376469135 }, "communicator.exchange": { "total": 0.010707121924497187, "count": 1, "is_parallel": true, "self": 0.010707121924497187 }, "steps_from_proto": { "total": 0.0003314779605716467, "count": 1, "is_parallel": true, "self": 8.197687566280365e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00024950108490884304, "count": 2, "is_parallel": true, "self": 0.00024950108490884304 } } } } } } }, "UnityEnvironment.step": { "total": 446.5369283996988, "count": 232554, "is_parallel": true, "self": 15.271971918293275, "children": { "UnityEnvironment._generate_step_input": { "total": 27.871795365121216, "count": 232554, "is_parallel": true, "self": 27.871795365121216 }, "communicator.exchange": { "total": 369.429243697552, "count": 232554, "is_parallel": true, "self": 369.429243697552 }, "steps_from_proto": { "total": 33.96391741873231, "count": 232554, "is_parallel": true, "self": 12.997861071489751, "children": { "_process_rank_one_or_two_observation": { "total": 20.966056347242557, "count": 465108, "is_parallel": true, "self": 20.966056347242557 } } } } } } } } } } }, "trainer_advance": { "total": 250.5105189633323, "count": 232555, "self": 3.04386013711337, "children": { "process_trajectory": { "total": 84.52247758279555, "count": 232555, "self": 83.90497352986131, "children": { "RLTrainer._checkpoint": { "total": 0.6175040529342368, "count": 10, "self": 0.6175040529342368 } } }, "_update_policy": { "total": 162.94418124342337, "count": 97, "self": 131.56898693938274, "children": { "TorchPPOOptimizer.update": { "total": 31.375194304040633, "count": 2910, "self": 31.375194304040633 } } } } } } }, "trainer_threads": { "total": 5.799811333417892e-07, "count": 1, "self": 5.799811333417892e-07 }, "TrainerController._save_models": { "total": 0.058602505014277995, "count": 1, "self": 0.00100143498275429, "children": { "RLTrainer._checkpoint": { "total": 0.057601070031523705, "count": 1, "self": 0.057601070031523705 } } } } } } }