{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4707433879375458, "min": 0.4582747519016266, "max": 1.4006602764129639, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14062.046875, "min": 13696.916015625, "max": 42490.4296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49425941705703735, "min": -0.09521704167127609, "max": 0.5955262184143066, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.39263916015625, "min": -22.947307586669922, "max": 167.34286499023438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04150329902768135, "min": -0.07348424941301346, "max": 0.2565966844558716, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.62092399597168, "min": -19.252872467041016, "max": 62.352996826171875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0667217821618953, "min": 0.06626975769054794, "max": 0.07339572264828753, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9341049502665342, "min": 0.5137700585380127, "max": 1.0833451482615728, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013713637445642449, "min": 0.0003142660971619891, "max": 0.015194738899784472, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19199092423899428, "min": 0.0037711931659438697, "max": 0.22260733586153947, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3675189727642854e-06, "min": 7.3675189727642854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001031452656187, "min": 0.0001031452656187, "max": 0.0033749074750308995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245580714285715, "min": 0.10245580714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343813, "min": 1.3886848, "max": 2.6172831, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002553351335714286, "min": 0.0002553351335714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035746918700000005, "min": 0.0035746918700000005, "max": 0.11251441309000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009439700283110142, "min": 0.009439700283110142, "max": 0.44988831877708435, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13215580582618713, "min": 0.13215580582618713, "max": 3.1492183208465576, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 390.7439024390244, "min": 308.9891304347826, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32041.0, "min": 15984.0, "max": 34276.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5360731542473887, "min": -1.0000000521540642, "max": 1.6475173707889474, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.95799864828587, "min": -29.99700155109167, "max": 151.57159811258316, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5360731542473887, "min": -1.0000000521540642, "max": 1.6475173707889474, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.95799864828587, "min": -29.99700155109167, "max": 151.57159811258316, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038783439980273594, "min": 0.031633065229075524, "max": 8.77097640838474, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1802420783824346, "min": 2.9102420010749483, "max": 140.33562253415585, "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": "1731181691", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731183995" }, "total": 2303.899785095, "count": 1, "self": 0.5771192659994995, "children": { "run_training.setup": { "total": 0.054254548000017166, "count": 1, "self": 0.054254548000017166 }, "TrainerController.start_learning": { "total": 2303.268411281, "count": 1, "self": 1.4494246899894279, "children": { "TrainerController._reset_env": { "total": 2.1723322500000677, "count": 1, "self": 2.1723322500000677 }, "TrainerController.advance": { "total": 2299.5627432060105, "count": 63992, "self": 1.3990294199311393, "children": { "env_step": { "total": 1607.945869146013, "count": 63992, "self": 1455.1959636300217, "children": { "SubprocessEnvManager._take_step": { "total": 151.90611255601596, "count": 63992, "self": 4.66954519902356, "children": { "TorchPolicy.evaluate": { "total": 147.2365673569924, "count": 62566, "self": 147.2365673569924 } } }, "workers": { "total": 0.8437929599751897, "count": 63992, "self": 0.0, "children": { "worker_root": { "total": 2297.85913017607, "count": 63992, "is_parallel": true, "self": 961.8046121321017, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020155199999862816, "count": 1, "is_parallel": true, "self": 0.0006568750000042201, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013586449999820616, "count": 8, "is_parallel": true, "self": 0.0013586449999820616 } } }, "UnityEnvironment.step": { "total": 0.04781041999990521, "count": 1, "is_parallel": true, "self": 0.0006455980000055206, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005063729998937561, "count": 1, "is_parallel": true, "self": 0.0005063729998937561 }, "communicator.exchange": { "total": 0.0447787260000041, "count": 1, "is_parallel": true, "self": 0.0447787260000041 }, "steps_from_proto": { "total": 0.0018797230000018317, "count": 1, "is_parallel": true, "self": 0.00040575899981831753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014739640001835141, "count": 8, "is_parallel": true, "self": 0.0014739640001835141 } } } } } } }, "UnityEnvironment.step": { "total": 1336.054518043968, "count": 63991, "is_parallel": true, "self": 33.44107493411798, "children": { "UnityEnvironment._generate_step_input": { "total": 23.5869360149793, "count": 63991, "is_parallel": true, "self": 23.5869360149793 }, "communicator.exchange": { "total": 1180.1861233109705, "count": 63991, "is_parallel": true, "self": 1180.1861233109705 }, "steps_from_proto": { "total": 98.84038378390028, "count": 63991, "is_parallel": true, "self": 20.45434779097627, "children": { "_process_rank_one_or_two_observation": { "total": 78.38603599292401, "count": 511928, "is_parallel": true, "self": 78.38603599292401 } } } } } } } } } } }, "trainer_advance": { "total": 690.2178446400663, "count": 63992, "self": 2.743988763077823, "children": { "process_trajectory": { "total": 135.27014328898895, "count": 63992, "self": 135.0631713209891, "children": { "RLTrainer._checkpoint": { "total": 0.2069719679998343, "count": 2, "self": 0.2069719679998343 } } }, "_update_policy": { "total": 552.2037125879996, "count": 455, "self": 310.86015655104063, "children": { "TorchPPOOptimizer.update": { "total": 241.34355603695894, "count": 22815, "self": 241.34355603695894 } } } } } } }, "trainer_threads": { "total": 1.3700000636163168e-06, "count": 1, "self": 1.3700000636163168e-06 }, "TrainerController._save_models": { "total": 0.08390976500004399, "count": 1, "self": 0.001578188000166847, "children": { "RLTrainer._checkpoint": { "total": 0.08233157699987714, "count": 1, "self": 0.08233157699987714 } } } } } } }