{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4093056917190552, "min": 1.4093056917190552, "max": 1.4312716722488403, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69709.8984375, "min": 69506.15625, "max": 76491.734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.49338374291115, "min": 86.17073170731707, "max": 424.2118644067797, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49458.0, "min": 48837.0, "max": 50187.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999985.0, "min": 49449.0, "max": 1999985.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999985.0, "min": 49449.0, "max": 1999985.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3720998764038086, "min": 0.1257525086402893, "max": 2.4413962364196777, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1254.8408203125, "min": 14.713043212890625, "max": 1349.5098876953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.657958654239633, "min": 1.7533509644687686, "max": 4.03097974007227, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1935.0601280927658, "min": 205.14206284284592, "max": 2204.759352862835, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.657958654239633, "min": 1.7533509644687686, "max": 4.03097974007227, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1935.0601280927658, "min": 205.14206284284592, "max": 2204.759352862835, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01593951335226949, "min": 0.012199712907507394, "max": 0.02117176560811155, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04781854005680847, "min": 0.024399425815014787, "max": 0.05288294092363988, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04836036658121481, "min": 0.02286210260871384, "max": 0.06512601673603058, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14508109974364441, "min": 0.046170519292354585, "max": 0.17829087190330029, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.547998817366671e-06, "min": 3.547998817366671e-06, "max": 0.00029529855156714996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0643996452100013e-05, "min": 1.0643996452100013e-05, "max": 0.0008441752686082499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118263333333333, "min": 0.10118263333333333, "max": 0.19843285000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035479, "min": 0.20749725000000008, "max": 0.5813917500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.90134033333334e-05, "min": 6.90134033333334e-05, "max": 0.004921799215, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020704021000000021, "min": 0.00020704021000000021, "max": 0.014071448325000003, "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": "1678187263", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678192314" }, "total": 5051.8787399660005, "count": 1, "self": 0.7037851770000998, "children": { "run_training.setup": { "total": 0.23463495300001114, "count": 1, "self": 0.23463495300001114 }, "TrainerController.start_learning": { "total": 5050.9403198360005, "count": 1, "self": 8.696856835083963, "children": { "TrainerController._reset_env": { "total": 9.557018606000042, "count": 1, "self": 9.557018606000042 }, "TrainerController.advance": { "total": 5032.553397236918, "count": 231867, "self": 9.67335531581557, "children": { "env_step": { "total": 3281.0639944201357, "count": 231867, "self": 2799.7257796933363, "children": { "SubprocessEnvManager._take_step": { "total": 475.1635666408515, "count": 231867, "self": 32.69880358596271, "children": { "TorchPolicy.evaluate": { "total": 442.4647630548888, "count": 222933, "self": 66.32888769610668, "children": { "TorchPolicy.sample_actions": { "total": 376.13587535878213, "count": 222933, "self": 376.13587535878213 } } } } }, "workers": { "total": 6.174648085947865, "count": 231867, "self": 0.0, "children": { "worker_root": { "total": 5032.406899796111, "count": 231867, "is_parallel": true, "self": 2794.0508842901304, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012185479999970994, "count": 1, "is_parallel": true, "self": 0.0004239699999857294, "children": { "_process_rank_one_or_two_observation": { "total": 0.00079457800001137, "count": 2, "is_parallel": true, "self": 0.00079457800001137 } } }, "UnityEnvironment.step": { "total": 0.03665204200001426, "count": 1, "is_parallel": true, "self": 0.00045391999998400934, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027404200000091805, "count": 1, "is_parallel": true, "self": 0.00027404200000091805 }, "communicator.exchange": { "total": 0.035012374000018553, "count": 1, "is_parallel": true, "self": 0.035012374000018553 }, "steps_from_proto": { "total": 0.0009117060000107813, "count": 1, "is_parallel": true, "self": 0.0002854999999613028, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006262060000494785, "count": 2, "is_parallel": true, "self": 0.0006262060000494785 } } } } } } }, "UnityEnvironment.step": { "total": 2238.356015505981, "count": 231866, "is_parallel": true, "self": 69.80054739529396, "children": { "UnityEnvironment._generate_step_input": { "total": 100.20562726984559, "count": 231866, "is_parallel": true, "self": 100.20562726984559 }, "communicator.exchange": { "total": 1909.2667613380154, "count": 231866, "is_parallel": true, "self": 1909.2667613380154 }, "steps_from_proto": { "total": 159.0830795028259, "count": 231866, "is_parallel": true, "self": 58.586043584181596, "children": { "_process_rank_one_or_two_observation": { "total": 100.49703591864431, "count": 463732, "is_parallel": true, "self": 100.49703591864431 } } } } } } } } } } }, "trainer_advance": { "total": 1741.816047500966, "count": 231867, "self": 14.544137809874883, "children": { "process_trajectory": { "total": 280.5636381170903, "count": 231867, "self": 279.0379551520909, "children": { "RLTrainer._checkpoint": { "total": 1.5256829649994188, "count": 10, "self": 1.5256829649994188 } } }, "_update_policy": { "total": 1446.708271574001, "count": 97, "self": 379.618941483998, "children": { "TorchPPOOptimizer.update": { "total": 1067.089330090003, "count": 2910, "self": 1067.089330090003 } } } } } } }, "trainer_threads": { "total": 1.0199992175330408e-06, "count": 1, "self": 1.0199992175330408e-06 }, "TrainerController._save_models": { "total": 0.13304613799937215, "count": 1, "self": 0.0033979989993895288, "children": { "RLTrainer._checkpoint": { "total": 0.12964813899998262, "count": 1, "self": 0.12964813899998262 } } } } } } }