{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4083523750305176, "min": 1.4083523750305176, "max": 1.4262501001358032, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70142.9921875, "min": 69518.796875, "max": 74575.59375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.91119691119691, "min": 88.79204339963833, "max": 419.66386554621846, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49682.0, "min": 48897.0, "max": 50113.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999686.0, "min": 49970.0, "max": 1999686.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999686.0, "min": 49970.0, "max": 1999686.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.411769390106201, "min": 0.06880888342857361, "max": 2.466500759124756, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1249.2965087890625, "min": 8.1194486618042, "max": 1317.36767578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7342257704513875, "min": 1.806613298795991, "max": 3.903749147858795, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1934.3289490938187, "min": 213.18036925792694, "max": 2018.238309442997, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7342257704513875, "min": 1.806613298795991, "max": 3.903749147858795, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1934.3289490938187, "min": 213.18036925792694, "max": 2018.238309442997, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019309963581811945, "min": 0.014337907099979931, "max": 0.020831783577644578, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03861992716362389, "min": 0.028675814199959862, "max": 0.06249535073293373, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.048746108636260034, "min": 0.02397359042531914, "max": 0.057302498072385785, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09749221727252007, "min": 0.04878056229402622, "max": 0.16375692375004292, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.519523493524989e-06, "min": 4.519523493524989e-06, "max": 0.00029526232657922495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.039046987049979e-06, "min": 9.039046987049979e-06, "max": 0.0008436499687833499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10150647499999998, "min": 0.10150647499999998, "max": 0.19842077500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20301294999999997, "min": 0.20301294999999997, "max": 0.58121665, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.51731024999998e-05, "min": 8.51731024999998e-05, "max": 0.0049211966725, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001703462049999996, "min": 0.0001703462049999996, "max": 0.014062710834999999, "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": "1670531815", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/demi/miniconda3/envs/rl/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": "1.23.5", "end_time_seconds": "1670533471" }, "total": 1655.8096567389998, "count": 1, "self": 0.27447660600000745, "children": { "run_training.setup": { "total": 0.018073618000016722, "count": 1, "self": 0.018073618000016722 }, "TrainerController.start_learning": { "total": 1655.5171065149998, "count": 1, "self": 3.925095257987323, "children": { "TrainerController._reset_env": { "total": 2.050603133000095, "count": 1, "self": 2.050603133000095 }, "TrainerController.advance": { "total": 1649.440100570012, "count": 231686, "self": 4.115957287145193, "children": { "env_step": { "total": 1128.4056247377407, "count": 231686, "self": 954.8629584268783, "children": { "SubprocessEnvManager._take_step": { "total": 170.93459446869338, "count": 231686, "self": 11.070384887736964, "children": { "TorchPolicy.evaluate": { "total": 159.8642095809564, "count": 222941, "self": 23.834167820835773, "children": { "TorchPolicy.sample_actions": { "total": 136.03004176012064, "count": 222941, "self": 136.03004176012064 } } } } }, "workers": { "total": 2.608071842169011, "count": 231686, "self": 0.0, "children": { "worker_root": { "total": 1649.35398944718, "count": 231686, "is_parallel": true, "self": 893.0345080390789, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0004880299998148985, "count": 1, "is_parallel": true, "self": 0.0001628239997444325, "children": { "_process_rank_one_or_two_observation": { "total": 0.00032520600007046596, "count": 2, "is_parallel": true, "self": 0.00032520600007046596 } } }, "UnityEnvironment.step": { "total": 0.02174185000012585, "count": 1, "is_parallel": true, "self": 0.00014603799991164124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001246880001417594, "count": 1, "is_parallel": true, "self": 0.0001246880001417594 }, "communicator.exchange": { "total": 0.021147264999854087, "count": 1, "is_parallel": true, "self": 0.021147264999854087 }, "steps_from_proto": { "total": 0.0003238590002183628, "count": 1, "is_parallel": true, "self": 0.00010707400042520021, "children": { "_process_rank_one_or_two_observation": { "total": 0.00021678499979316257, "count": 2, "is_parallel": true, "self": 0.00021678499979316257 } } } } } } }, "UnityEnvironment.step": { "total": 756.3194814081012, "count": 231685, "is_parallel": true, "self": 26.830537503349206, "children": { "UnityEnvironment._generate_step_input": { "total": 53.28389046001712, "count": 231685, "is_parallel": true, "self": 53.28389046001712 }, "communicator.exchange": { "total": 614.1934714351569, "count": 231685, "is_parallel": true, "self": 614.1934714351569 }, "steps_from_proto": { "total": 62.01158200957798, "count": 231685, "is_parallel": true, "self": 26.03166037858, "children": { "_process_rank_one_or_two_observation": { "total": 35.97992163099798, "count": 463370, "is_parallel": true, "self": 35.97992163099798 } } } } } } } } } } }, "trainer_advance": { "total": 516.9185185451261, "count": 231686, "self": 5.923911587091425, "children": { "process_trajectory": { "total": 109.7783471190287, "count": 231686, "self": 109.36277365602746, "children": { "RLTrainer._checkpoint": { "total": 0.41557346300123754, "count": 4, "self": 0.41557346300123754 } } }, "_update_policy": { "total": 401.21625983900594, "count": 96, "self": 173.03493737801045, "children": { "TorchPPOOptimizer.update": { "total": 228.1813224609955, "count": 2880, "self": 228.1813224609955 } } } } } } }, "trainer_threads": { "total": 7.839998943381943e-07, "count": 1, "self": 7.839998943381943e-07 }, "TrainerController._save_models": { "total": 0.10130677000051946, "count": 1, "self": 0.0013498760008587851, "children": { "RLTrainer._checkpoint": { "total": 0.09995689399966068, "count": 1, "self": 0.09995689399966068 } } } } } } }