{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48279398679733276, "min": 0.4668481945991516, "max": 1.5080304145812988, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14530.16796875, "min": 13878.462890625, "max": 45747.609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4767856299877167, "min": -0.07910780608654022, "max": 0.4767856299877167, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.59283447265625, "min": -19.144088745117188, "max": 131.59283447265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025797370821237564, "min": 0.005823015235364437, "max": 0.6202724575996399, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.120074272155762, "min": 1.525629997253418, "max": 149.48565673828125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04704560387402861, "min": 0.045530874499187725, "max": 0.055124202285154786, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3293192271182003, "min": 0.22049680914061914, "max": 0.4059580573521089, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014473694906060009, "min": 0.0009505308344932463, "max": 0.015404542200320231, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10131586434242006, "min": 0.005703185006959478, "max": 0.10427303562755696, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.465983225657139e-06, "min": 7.465983225657139e-06, "max": 0.00029544960151679995, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.226188257959997e-05, "min": 5.226188257959997e-05, "max": 0.0018145749951416997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248862857142857, "min": 0.10248862857142857, "max": 0.1984832, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7174204, "min": 0.7174204, "max": 1.3481356999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002586139942857142, "min": 0.0002586139942857142, "max": 0.00984847168, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0018102979599999994, "min": 0.0018102979599999994, "max": 0.060495344170000014, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.023293668404221535, "min": 0.023293668404221535, "max": 0.9480493068695068, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1630556732416153, "min": 0.1630556732416153, "max": 3.7921972274780273, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 419.50666666666666, "min": 419.0735294117647, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31463.0, "min": 15984.0, "max": 32870.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.445055979390939, "min": -1.0000000521540642, "max": 1.4562029185540535, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 108.37919845432043, "min": -30.54300171136856, "max": 108.37919845432043, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.445055979390939, "min": -1.0000000521540642, "max": 1.4562029185540535, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 108.37919845432043, "min": -30.54300171136856, "max": 108.37919845432043, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0999067586613819, "min": 0.0999067586613819, "max": 13.12626770325005, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 7.4930068996036425, "min": 6.9794198769377545, "max": 253.85612292587757, "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": "1771930305", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/home/vinhnt/projects/deep-rl-class/.venv/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1771931921" }, "total": 1616.5965752210031, "count": 1, "self": 0.2727716119989054, "children": { "run_training.setup": { "total": 0.020728142000734806, "count": 1, "self": 0.020728142000734806 }, "TrainerController.start_learning": { "total": 1616.3030754670035, "count": 1, "self": 1.2626327461985056, "children": { "TrainerController._reset_env": { "total": 2.78389424299894, "count": 1, "self": 2.78389424299894 }, "TrainerController.advance": { "total": 1612.1778930788023, "count": 63613, "self": 0.9921539633724024, "children": { "env_step": { "total": 1205.8347173556394, "count": 63613, "self": 1001.8841754638815, "children": { "SubprocessEnvManager._take_step": { "total": 203.09575529623544, "count": 63613, "self": 3.2603687888549757, "children": { "TorchPolicy.evaluate": { "total": 199.83538650738046, "count": 62567, "self": 199.83538650738046 } } }, "workers": { "total": 0.8547865955224552, "count": 63613, "self": 0.0, "children": { "worker_root": { "total": 1613.5029699335319, "count": 63613, "is_parallel": true, "self": 683.9699394712625, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015456839973921888, "count": 1, "is_parallel": true, "self": 0.000570030006201705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009756539911904838, "count": 8, "is_parallel": true, "self": 0.0009756539911904838 } } }, "UnityEnvironment.step": { "total": 0.02961623699957272, "count": 1, "is_parallel": true, "self": 0.00015586099834763445, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016079800116131082, "count": 1, "is_parallel": true, "self": 0.00016079800116131082 }, "communicator.exchange": { "total": 0.02875959400262218, "count": 1, "is_parallel": true, "self": 0.02875959400262218 }, "steps_from_proto": { "total": 0.0005399839974415954, "count": 1, "is_parallel": true, "self": 0.0001214749863720499, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004185090110695455, "count": 8, "is_parallel": true, "self": 0.0004185090110695455 } } } } } } }, "UnityEnvironment.step": { "total": 929.5330304622694, "count": 63612, "is_parallel": true, "self": 10.833165397991252, "children": { "UnityEnvironment._generate_step_input": { "total": 8.175232157889695, "count": 63612, "is_parallel": true, "self": 8.175232157889695 }, "communicator.exchange": { "total": 879.3255521948158, "count": 63612, "is_parallel": true, "self": 879.3255521948158 }, "steps_from_proto": { "total": 31.199080711572606, "count": 63612, "is_parallel": true, "self": 7.705334247206338, "children": { "_process_rank_one_or_two_observation": { "total": 23.493746464366268, "count": 508896, "is_parallel": true, "self": 23.493746464366268 } } } } } } } } } } }, "trainer_advance": { "total": 405.35102175979046, "count": 63613, "self": 2.378476389669231, "children": { "process_trajectory": { "total": 101.89653607707078, "count": 63613, "self": 101.68482943307026, "children": { "RLTrainer._checkpoint": { "total": 0.21170664400051464, "count": 2, "self": 0.21170664400051464 } } }, "_update_policy": { "total": 301.07600929305045, "count": 233, "self": 160.076015411134, "children": { "TorchPPOOptimizer.update": { "total": 140.99999388191645, "count": 11526, "self": 140.99999388191645 } } } } } } }, "trainer_threads": { "total": 6.020054570399225e-07, "count": 1, "self": 6.020054570399225e-07 }, "TrainerController._save_models": { "total": 0.07865479699830757, "count": 1, "self": 0.0015611339986207895, "children": { "RLTrainer._checkpoint": { "total": 0.07709366299968679, "count": 1, "self": 0.07709366299968679 } } } } } } }