{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.440656304359436, "min": 1.440656304359436, "max": 1.440656304359436, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 43703.75, "min": 43703.75, "max": 43703.75, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.027442436665296555, "min": -0.027442436665296555, "max": -0.027442436665296555, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -6.503857612609863, "min": -6.503857612609863, "max": -6.503857612609863, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.27356621623039246, "min": 0.27356621623039246, "max": 0.27356621623039246, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 64.83518981933594, "min": 64.83518981933594, "max": 64.83518981933594, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07015726983621572, "min": 0.07015726983621572, "max": 0.07015726983621572, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.49110088885351, "min": 0.49110088885351, "max": 0.49110088885351, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007919887566315415, "min": 0.007919887566315415, "max": 0.007919887566315415, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0554392129642079, "min": 0.0554392129642079, "max": 0.0554392129642079, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00029838354339596195, "min": 0.00029838354339596195, "max": 0.00029838354339596195, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020886848037717336, "min": 0.0020886848037717336, "max": 0.0020886848037717336, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19946118095238097, "min": 0.19946118095238097, "max": 0.19946118095238097, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3962282666666668, "min": 1.3962282666666668, "max": 1.3962282666666668, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.009946171977142856, "min": 0.009946171977142856, "max": 0.009946171977142856, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.06962320384, "min": 0.06962320384, "max": 0.06962320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.526415228843689, "min": 0.526415228843689, "max": 0.526415228843689, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 3.6849067211151123, "min": 3.6849067211151123, "max": 3.6849067211151123, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 11.258648790419102, "min": 11.258648790419102, "max": 11.258648790419102, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 180.13838064670563, "min": 180.13838064670563, "max": 180.13838064670563, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1656923023", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --resume --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1656923110" }, "total": 86.40793276799968, "count": 1, "self": 0.2770667559998401, "children": { "run_training.setup": { "total": 0.04878476799967757, "count": 1, "self": 0.04878476799967757 }, "TrainerController.start_learning": { "total": 86.08208124400016, "count": 1, "self": 0.06614023100473787, "children": { "TrainerController._reset_env": { "total": 6.4205231289997755, "count": 1, "self": 6.4205231289997755 }, "TrainerController.advance": { "total": 79.39535842999567, "count": 2819, "self": 0.06401563601457383, "children": { "env_step": { "total": 48.148401287980505, "count": 2819, "self": 43.20649772196748, "children": { "SubprocessEnvManager._take_step": { "total": 4.909629248001693, "count": 2819, "self": 0.20992596698306443, "children": { "TorchPolicy.evaluate": { "total": 4.699703281018628, "count": 2818, "self": 1.585710538020976, "children": { "TorchPolicy.sample_actions": { "total": 3.1139927429976524, "count": 2818, "self": 3.1139927429976524 } } } } }, "workers": { "total": 0.03227431801133207, "count": 2818, "self": 0.0, "children": { "worker_root": { "total": 85.7363061749993, "count": 2818, "is_parallel": true, "self": 47.09216559199649, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018881139999393781, "count": 1, "is_parallel": true, "self": 0.0006898039987390803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011983100012002978, "count": 8, "is_parallel": true, "self": 0.0011983100012002978 } } }, "UnityEnvironment.step": { "total": 0.050796596000054706, "count": 1, "is_parallel": true, "self": 0.0005035890003455279, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033838899980764836, "count": 1, "is_parallel": true, "self": 0.00033838899980764836 }, "communicator.exchange": { "total": 0.04827354099961667, "count": 1, "is_parallel": true, "self": 0.04827354099961667 }, "steps_from_proto": { "total": 0.0016810770002848585, "count": 1, "is_parallel": true, "self": 0.000445900000158872, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012351770001259865, "count": 8, "is_parallel": true, "self": 0.0012351770001259865 } } } } } } }, "UnityEnvironment.step": { "total": 38.64414058300281, "count": 2817, "is_parallel": true, "self": 1.2224123129853979, "children": { "UnityEnvironment._generate_step_input": { "total": 1.0352337199947215, "count": 2817, "is_parallel": true, "self": 1.0352337199947215 }, "communicator.exchange": { "total": 32.16947123200907, "count": 2817, "is_parallel": true, "self": 32.16947123200907 }, "steps_from_proto": { "total": 4.2170233180136165, "count": 2817, "is_parallel": true, "self": 1.0222699240066504, "children": { "_process_rank_one_or_two_observation": { "total": 3.194753394006966, "count": 22536, "is_parallel": true, "self": 3.194753394006966 } } } } } } } } } } }, "trainer_advance": { "total": 31.18294150600059, "count": 2818, "self": 0.08227590699561915, "children": { "process_trajectory": { "total": 7.002250391004509, "count": 2818, "self": 7.002250391004509 }, "_update_policy": { "total": 24.09841520800046, "count": 11, "self": 9.608979676001582, "children": { "TorchPPOOptimizer.update": { "total": 14.489435531998879, "count": 990, "self": 14.489435531998879 } } } } } } }, "trainer_threads": { "total": 1.6349999896192458e-06, "count": 1, "self": 1.6349999896192458e-06 }, "TrainerController._save_models": { "total": 0.2000578189999942, "count": 1, "self": 0.003952618999846891, "children": { "RLTrainer._checkpoint": { "total": 0.1961052000001473, "count": 1, "self": 0.1961052000001473 } } } } } } }