{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4112077951431274, "min": 1.4112077951431274, "max": 1.431397795677185, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70512.40625, "min": 68839.65625, "max": 76231.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.65018315018315, "min": 87.32624113475177, "max": 402.241935483871, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49495.0, "min": 48973.0, "max": 50168.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999978.0, "min": 49757.0, "max": 1999978.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999978.0, "min": 49757.0, "max": 1999978.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3749239444732666, "min": 0.12880967557430267, "max": 2.4795451164245605, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1296.70849609375, "min": 15.84359073638916, "max": 1341.6650390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7211622908001853, "min": 1.960257695700095, "max": 3.89133353133238, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2031.7546107769012, "min": 241.11169657111168, "max": 2122.555369734764, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7211622908001853, "min": 1.960257695700095, "max": 3.89133353133238, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2031.7546107769012, "min": 241.11169657111168, "max": 2122.555369734764, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01777710614199653, "min": 0.013390343586191497, "max": 0.019378150918540386, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05333131842598959, "min": 0.026780687172382994, "max": 0.05716785095622376, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057286393269896506, "min": 0.022413383610546588, "max": 0.06110278932998578, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1718591798096895, "min": 0.044826767221093175, "max": 0.17702434572080772, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2113989295666728e-06, "min": 3.2113989295666728e-06, "max": 0.0002953488765503749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.634196788700018e-06, "min": 9.634196788700018e-06, "max": 0.00084400396866535, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107043333333336, "min": 0.10107043333333336, "max": 0.19844962500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032113000000001, "min": 0.2072642, "max": 0.5813346500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.341462333333342e-05, "min": 6.341462333333342e-05, "max": 0.004922636287500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019024387000000028, "min": 0.00019024387000000028, "max": 0.014068599034999997, "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": "1675268463", "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": "1.21.6", "end_time_seconds": "1675270611" }, "total": 2147.949479281, "count": 1, "self": 0.39202289300010307, "children": { "run_training.setup": { "total": 0.1102767240000162, "count": 1, "self": 0.1102767240000162 }, "TrainerController.start_learning": { "total": 2147.447179664, "count": 1, "self": 3.8141998890082505, "children": { "TrainerController._reset_env": { "total": 10.951565389999985, "count": 1, "self": 10.951565389999985 }, "TrainerController.advance": { "total": 2132.5726241899924, "count": 231887, "self": 3.8789998219740482, "children": { "env_step": { "total": 1683.3327535640688, "count": 231887, "self": 1415.682696567967, "children": { "SubprocessEnvManager._take_step": { "total": 265.18979678702385, "count": 231887, "self": 14.122745660993246, "children": { "TorchPolicy.evaluate": { "total": 251.0670511260306, "count": 222957, "self": 62.91120465293511, "children": { "TorchPolicy.sample_actions": { "total": 188.1558464730955, "count": 222957, "self": 188.1558464730955 } } } } }, "workers": { "total": 2.460260209078001, "count": 231887, "self": 0.0, "children": { "worker_root": { "total": 2139.6635877679378, "count": 231887, "is_parallel": true, "self": 975.0689119070212, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018992999999909443, "count": 1, "is_parallel": true, "self": 0.00032686600002307387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015724339999678705, "count": 2, "is_parallel": true, "self": 0.0015724339999678705 } } }, "UnityEnvironment.step": { "total": 0.026017767000098502, "count": 1, "is_parallel": true, "self": 0.0002534180000566266, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017469600004460517, "count": 1, "is_parallel": true, "self": 0.00017469600004460517 }, "communicator.exchange": { "total": 0.0247188590000178, "count": 1, "is_parallel": true, "self": 0.0247188590000178 }, "steps_from_proto": { "total": 0.0008707939999794689, "count": 1, "is_parallel": true, "self": 0.00039915000013479585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004716439998446731, "count": 2, "is_parallel": true, "self": 0.0004716439998446731 } } } } } } }, "UnityEnvironment.step": { "total": 1164.5946758609166, "count": 231886, "is_parallel": true, "self": 33.987407672867676, "children": { "UnityEnvironment._generate_step_input": { "total": 74.73725375298147, "count": 231886, "is_parallel": true, "self": 74.73725375298147 }, "communicator.exchange": { "total": 967.4283188779792, "count": 231886, "is_parallel": true, "self": 967.4283188779792 }, "steps_from_proto": { "total": 88.44169555708822, "count": 231886, "is_parallel": true, "self": 36.32322400623343, "children": { "_process_rank_one_or_two_observation": { "total": 52.11847155085479, "count": 463772, "is_parallel": true, "self": 52.11847155085479 } } } } } } } } } } }, "trainer_advance": { "total": 445.36087080394964, "count": 231887, "self": 6.031342298854497, "children": { "process_trajectory": { "total": 139.35529513809502, "count": 231887, "self": 138.27140636609522, "children": { "RLTrainer._checkpoint": { "total": 1.0838887719997956, "count": 10, "self": 1.0838887719997956 } } }, "_update_policy": { "total": 299.9742333670001, "count": 97, "self": 247.1848083979968, "children": { "TorchPPOOptimizer.update": { "total": 52.789424969003335, "count": 2910, "self": 52.789424969003335 } } } } } } }, "trainer_threads": { "total": 8.519996299582999e-07, "count": 1, "self": 8.519996299582999e-07 }, "TrainerController._save_models": { "total": 0.10878934299989851, "count": 1, "self": 0.002597196999886364, "children": { "RLTrainer._checkpoint": { "total": 0.10619214600001214, "count": 1, "self": 0.10619214600001214 } } } } } } }