{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4794846177101135, "min": 0.4622275233268738, "max": 1.3950453996658325, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14392.2099609375, "min": 13807.66015625, "max": 42320.09765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4140358567237854, "min": -0.09726379811763763, "max": 0.4140358567237854, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.96160888671875, "min": -23.440574645996094, "max": 110.96160888671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.6623600125312805, "min": -0.03341243416070938, "max": 0.6856850385665894, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 177.51248168945312, "min": -8.687232971191406, "max": 177.51248168945312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06785737925730202, "min": 0.06419577596644632, "max": 0.07385120685759983, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9500033096022283, "min": 0.4851599499013211, "max": 1.0366720305065231, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.09548289463453416, "min": 0.0010564292909853116, "max": 0.09548289463453416, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.3367605248834782, "min": 0.007440665819913925, "max": 1.3367605248834782, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.619047460350003e-06, "min": 7.619047460350003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010666666444490005, "min": 0.00010666666444490005, "max": 0.0033829160723614, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253965000000001, "min": 0.10253965000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355551000000002, "min": 1.3691136000000002, "max": 2.5276386000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026371103500000015, "min": 0.00026371103500000015, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036919544900000023, "min": 0.0036919544900000023, "max": 0.11279109613999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013355172239243984, "min": 0.013355172239243984, "max": 0.6106462478637695, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18697240948677063, "min": 0.18697240948677063, "max": 4.274523735046387, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 470.8767123287671, "min": 470.8767123287671, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 34374.0, "min": 15984.0, "max": 34374.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3414972686284297, "min": -1.0000000521540642, "max": 1.3414972686284297, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.2707978785038, "min": -32.000001668930054, "max": 99.2707978785038, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3414972686284297, "min": -1.0000000521540642, "max": 1.3414972686284297, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.2707978785038, "min": -32.000001668930054, "max": 99.2707978785038, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06523465442729208, "min": 0.06523465442729208, "max": 14.013258224353194, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.827364427619614, "min": 3.9616701603954425, "max": 224.2121315896511, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718875263", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718877196" }, "total": 1933.1731796900003, "count": 1, "self": 0.4876872340000773, "children": { "run_training.setup": { "total": 0.04498997700011387, "count": 1, "self": 0.04498997700011387 }, "TrainerController.start_learning": { "total": 1932.6405024790001, "count": 1, "self": 1.1779157480586946, "children": { "TrainerController._reset_env": { "total": 1.9964453789998515, "count": 1, "self": 1.9964453789998515 }, "TrainerController.advance": { "total": 1929.3819430759422, "count": 63436, "self": 1.222676906984816, "children": { "env_step": { "total": 1329.8283801368843, "count": 63436, "self": 1209.6301288487211, "children": { "SubprocessEnvManager._take_step": { "total": 119.47888917711498, "count": 63436, "self": 4.313774692193874, "children": { "TorchPolicy.evaluate": { "total": 115.1651144849211, "count": 62572, "self": 115.1651144849211 } } }, "workers": { "total": 0.7193621110482127, "count": 63436, "self": 0.0, "children": { "worker_root": { "total": 1928.4458053069538, "count": 63436, "is_parallel": true, "self": 825.0083111809145, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019667930000650813, "count": 1, "is_parallel": true, "self": 0.0006452680008806055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013215249991844757, "count": 8, "is_parallel": true, "self": 0.0013215249991844757 } } }, "UnityEnvironment.step": { "total": 0.04799951899985899, "count": 1, "is_parallel": true, "self": 0.0005699469993487583, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004976430000169785, "count": 1, "is_parallel": true, "self": 0.0004976430000169785 }, "communicator.exchange": { "total": 0.045333633000154805, "count": 1, "is_parallel": true, "self": 0.045333633000154805 }, "steps_from_proto": { "total": 0.0015982960003384505, "count": 1, "is_parallel": true, "self": 0.0003394539999135304, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012588420004249201, "count": 8, "is_parallel": true, "self": 0.0012588420004249201 } } } } } } }, "UnityEnvironment.step": { "total": 1103.4374941260394, "count": 63435, "is_parallel": true, "self": 33.0445942449287, "children": { "UnityEnvironment._generate_step_input": { "total": 22.711084965036207, "count": 63435, "is_parallel": true, "self": 22.711084965036207 }, "communicator.exchange": { "total": 953.9838238000175, "count": 63435, "is_parallel": true, "self": 953.9838238000175 }, "steps_from_proto": { "total": 93.69799111605698, "count": 63435, "is_parallel": true, "self": 18.141289109104036, "children": { "_process_rank_one_or_two_observation": { "total": 75.55670200695295, "count": 507480, "is_parallel": true, "self": 75.55670200695295 } } } } } } } } } } }, "trainer_advance": { "total": 598.3308860320731, "count": 63436, "self": 2.3058565101109707, "children": { "process_trajectory": { "total": 114.43350881294828, "count": 63436, "self": 114.24616521894859, "children": { "RLTrainer._checkpoint": { "total": 0.18734359399968525, "count": 2, "self": 0.18734359399968525 } } }, "_update_policy": { "total": 481.5915207090138, "count": 438, "self": 285.26964545199826, "children": { "TorchPPOOptimizer.update": { "total": 196.32187525701556, "count": 22827, "self": 196.32187525701556 } } } } } } }, "trainer_threads": { "total": 8.859997251420282e-07, "count": 1, "self": 8.859997251420282e-07 }, "TrainerController._save_models": { "total": 0.08419738999964466, "count": 1, "self": 0.0013915290001023095, "children": { "RLTrainer._checkpoint": { "total": 0.08280586099954235, "count": 1, "self": 0.08280586099954235 } } } } } } }