{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405096173286438, "min": 1.405096173286438, "max": 1.4278452396392822, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71512.3671875, "min": 69504.1015625, "max": 78134.9453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.0368932038835, "min": 87.929203539823, "max": 390.359375, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49459.0, "min": 48877.0, "max": 50370.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999956.0, "min": 49819.0, "max": 1999956.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999956.0, "min": 49819.0, "max": 1999956.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.407031297683716, "min": 0.16417032480239868, "max": 2.418837308883667, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1239.62109375, "min": 20.84963035583496, "max": 1336.725830078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6895401679196405, "min": 1.7085079872232722, "max": 3.8478726797787717, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1900.1131864786148, "min": 216.98051437735558, "max": 2109.2286297678947, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6895401679196405, "min": 1.7085079872232722, "max": 3.8478726797787717, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1900.1131864786148, "min": 216.98051437735558, "max": 2109.2286297678947, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01862812927219137, "min": 0.013632917058324286, "max": 0.020069176292033968, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.055884387816574115, "min": 0.027265834116648572, "max": 0.0602075288761019, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05130517950488461, "min": 0.022412906959652902, "max": 0.06795423088802231, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15391553851465384, "min": 0.044825813919305804, "max": 0.20386269266406695, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.291348902916656e-06, "min": 3.291348902916656e-06, "max": 0.000295307926564025, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.874046708749968e-06, "min": 9.874046708749968e-06, "max": 0.0008441340186219998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109708333333338, "min": 0.10109708333333338, "max": 0.19843597500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032912500000001, "min": 0.20732735, "max": 0.5813780000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.474445833333318e-05, "min": 6.474445833333318e-05, "max": 0.004921955152500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001942333749999995, "min": 0.0001942333749999995, "max": 0.014070762200000001, "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": "1673485971", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1.21.6", "end_time_seconds": "1673488886" }, "total": 2915.121825207, "count": 1, "self": 0.49990317099991444, "children": { "run_training.setup": { "total": 0.12420975499998121, "count": 1, "self": 0.12420975499998121 }, "TrainerController.start_learning": { "total": 2914.497712281, "count": 1, "self": 5.954665349107927, "children": { "TrainerController._reset_env": { "total": 9.57741598900003, "count": 1, "self": 9.57741598900003 }, "TrainerController.advance": { "total": 2898.827271838892, "count": 231984, "self": 5.964732500996888, "children": { "env_step": { "total": 2340.415088047938, "count": 231984, "self": 1961.6297780200332, "children": { "SubprocessEnvManager._take_step": { "total": 374.80294091002736, "count": 231984, "self": 19.436984463030683, "children": { "TorchPolicy.evaluate": { "total": 355.3659564469967, "count": 223010, "self": 89.32113400301586, "children": { "TorchPolicy.sample_actions": { "total": 266.0448224439808, "count": 223010, "self": 266.0448224439808 } } } } }, "workers": { "total": 3.9823691178772265, "count": 231984, "self": 0.0, "children": { "worker_root": { "total": 2902.811382582028, "count": 231984, "is_parallel": true, "self": 1305.9670061470442, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023186829999986003, "count": 1, "is_parallel": true, "self": 0.0003895839999472628, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019290990000513375, "count": 2, "is_parallel": true, "self": 0.0019290990000513375 } } }, "UnityEnvironment.step": { "total": 0.05879142200001297, "count": 1, "is_parallel": true, "self": 0.0003401839999810363, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002058300000271629, "count": 1, "is_parallel": true, "self": 0.0002058300000271629 }, "communicator.exchange": { "total": 0.05717591799998445, "count": 1, "is_parallel": true, "self": 0.05717591799998445 }, "steps_from_proto": { "total": 0.0010694900000203234, "count": 1, "is_parallel": true, "self": 0.0004791989999830548, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005902910000372685, "count": 2, "is_parallel": true, "self": 0.0005902910000372685 } } } } } } }, "UnityEnvironment.step": { "total": 1596.8443764349836, "count": 231983, "is_parallel": true, "self": 44.44580397189088, "children": { "UnityEnvironment._generate_step_input": { "total": 97.19869662901283, "count": 231983, "is_parallel": true, "self": 97.19869662901283 }, "communicator.exchange": { "total": 1333.0141758769537, "count": 231983, "is_parallel": true, "self": 1333.0141758769537 }, "steps_from_proto": { "total": 122.18569995712625, "count": 231983, "is_parallel": true, "self": 51.25963093419125, "children": { "_process_rank_one_or_two_observation": { "total": 70.926069022935, "count": 463966, "is_parallel": true, "self": 70.926069022935 } } } } } } } } } } }, "trainer_advance": { "total": 552.4474512899574, "count": 231984, "self": 9.46510789592162, "children": { "process_trajectory": { "total": 182.71532540403354, "count": 231984, "self": 181.3716512290335, "children": { "RLTrainer._checkpoint": { "total": 1.3436741750000465, "count": 10, "self": 1.3436741750000465 } } }, "_update_policy": { "total": 360.2670179900023, "count": 97, "self": 301.1142359460141, "children": { "TorchPPOOptimizer.update": { "total": 59.15278204398817, "count": 2910, "self": 59.15278204398817 } } } } } } }, "trainer_threads": { "total": 9.890000001178123e-07, "count": 1, "self": 9.890000001178123e-07 }, "TrainerController._save_models": { "total": 0.1383581149998463, "count": 1, "self": 0.0024548900000809226, "children": { "RLTrainer._checkpoint": { "total": 0.13590322499976537, "count": 1, "self": 0.13590322499976537 } } } } } } }