{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4614676833152771, "min": 0.4614676833152771, "max": 1.4531798362731934, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13748.044921875, "min": 13748.044921875, "max": 44083.6640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.32395437359809875, "min": -0.09493961185216904, "max": 0.32395437359809875, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 84.55209350585938, "min": -22.81021499633789, "max": 84.55209350585938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005461744498461485, "min": -0.005461744498461485, "max": 0.554766058921814, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4255152940750122, "min": -1.4255152940750122, "max": 131.47955322265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07079249700538374, "min": 0.06493950840193355, "max": 0.0751172183934551, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9910949580753725, "min": 0.503419830384042, "max": 1.0653596335597446, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014041112589573876, "min": 0.0001058971845662172, "max": 0.025907027806295384, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19657557625403427, "min": 0.0013766633993608237, "max": 0.20026599757807603, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3777403979285645e-06, "min": 7.3777403979285645e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010328836557099991, "min": 0.00010328836557099991, "max": 0.003382023272659, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245921428571426, "min": 0.10245921428571426, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344289999999997, "min": 1.3691136000000002, "max": 2.527341, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000255675507142857, "min": 0.000255675507142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035794570999999977, "min": 0.0035794570999999977, "max": 0.1127613659, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013311672024428844, "min": 0.013311672024428844, "max": 0.6412887573242188, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18636341392993927, "min": 0.18636341392993927, "max": 4.489021301269531, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 508.46875, "min": 508.46875, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32542.0, "min": 15984.0, "max": 32542.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1461904484128196, "min": -1.0000000521540642, "max": 1.1791207284297582, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.20999825000763, "min": -32.000001668930054, "max": 72.20999825000763, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1461904484128196, "min": -1.0000000521540642, "max": 1.1791207284297582, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.20999825000763, "min": -32.000001668930054, "max": 72.20999825000763, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06890848509797323, "min": 0.06890848509797323, "max": 14.719729556702077, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.341234561172314, "min": 4.202804758679122, "max": 235.51567290723324, "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": "1740491185", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740493379" }, "total": 2194.258244417, "count": 1, "self": 0.5762395530000504, "children": { "run_training.setup": { "total": 0.020798137999918254, "count": 1, "self": 0.020798137999918254 }, "TrainerController.start_learning": { "total": 2193.661206726, "count": 1, "self": 1.4918594078617389, "children": { "TrainerController._reset_env": { "total": 2.2658494600000267, "count": 1, "self": 2.2658494600000267 }, "TrainerController.advance": { "total": 2189.8113694991384, "count": 63346, "self": 1.4644348290385096, "children": { "env_step": { "total": 1499.8649503630136, "count": 63346, "self": 1340.393202252083, "children": { "SubprocessEnvManager._take_step": { "total": 158.60658152286624, "count": 63346, "self": 4.7806833998156435, "children": { "TorchPolicy.evaluate": { "total": 153.8258981230506, "count": 62564, "self": 153.8258981230506 } } }, "workers": { "total": 0.8651665880643122, "count": 63346, "self": 0.0, "children": { "worker_root": { "total": 2188.4501663039364, "count": 63346, "is_parallel": true, "self": 961.6750679538482, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021431390000543615, "count": 1, "is_parallel": true, "self": 0.0006829520007158862, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014601869993384753, "count": 8, "is_parallel": true, "self": 0.0014601869993384753 } } }, "UnityEnvironment.step": { "total": 0.04889885099964886, "count": 1, "is_parallel": true, "self": 0.0005448549995890062, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044819499998993706, "count": 1, "is_parallel": true, "self": 0.00044819499998993706 }, "communicator.exchange": { "total": 0.04632270399997651, "count": 1, "is_parallel": true, "self": 0.04632270399997651 }, "steps_from_proto": { "total": 0.001583097000093403, "count": 1, "is_parallel": true, "self": 0.00033530099972267635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012477960003707267, "count": 8, "is_parallel": true, "self": 0.0012477960003707267 } } } } } } }, "UnityEnvironment.step": { "total": 1226.7750983500882, "count": 63345, "is_parallel": true, "self": 31.678933815397613, "children": { "UnityEnvironment._generate_step_input": { "total": 22.63190574592818, "count": 63345, "is_parallel": true, "self": 22.63190574592818 }, "communicator.exchange": { "total": 1077.0753920578964, "count": 63345, "is_parallel": true, "self": 1077.0753920578964 }, "steps_from_proto": { "total": 95.38886673086608, "count": 63345, "is_parallel": true, "self": 19.290146913565877, "children": { "_process_rank_one_or_two_observation": { "total": 76.0987198173002, "count": 506760, "is_parallel": true, "self": 76.0987198173002 } } } } } } } } } } }, "trainer_advance": { "total": 688.4819843070863, "count": 63346, "self": 2.665504691021397, "children": { "process_trajectory": { "total": 124.63323523008012, "count": 63346, "self": 124.42607277708021, "children": { "RLTrainer._checkpoint": { "total": 0.20716245299990987, "count": 2, "self": 0.20716245299990987 } } }, "_update_policy": { "total": 561.1832443859848, "count": 433, "self": 309.8094519309807, "children": { "TorchPPOOptimizer.update": { "total": 251.37379245500415, "count": 22890, "self": 251.37379245500415 } } } } } } }, "trainer_threads": { "total": 8.019997039809823e-07, "count": 1, "self": 8.019997039809823e-07 }, "TrainerController._save_models": { "total": 0.09212755699991249, "count": 1, "self": 0.001764455999364145, "children": { "RLTrainer._checkpoint": { "total": 0.09036310100054834, "count": 1, "self": 0.09036310100054834 } } } } } } }