{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9925450086593628, "min": 0.9847832918167114, "max": 1.466425895690918, "count": 5 }, "Pyramids.Policy.Entropy.sum": { "value": 30316.294921875, "min": 29496.228515625, "max": 44485.49609375, "count": 5 }, "Pyramids.Step.mean": { "value": 149970.0, "min": 29952.0, "max": 149970.0, "count": 5 }, "Pyramids.Step.sum": { "value": 149970.0, "min": 29952.0, "max": 149970.0, "count": 5 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.11928949505090714, "min": -0.11928949505090714, "max": 0.007646649144589901, "count": 5 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -28.748767852783203, "min": -28.748767852783203, "max": 1.812255859375, "count": 5 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.08848647773265839, "min": 0.08848647773265839, "max": 0.4663185477256775, "count": 5 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.325241088867188, "min": 21.325241088867188, "max": 110.51749420166016, "count": 5 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07245683489965793, "min": 0.07033540763214483, "max": 0.07588012771551118, "count": 5 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7970251838962372, "min": 0.5065388291637312, "max": 0.7970251838962372, "count": 5 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0005877865855996381, "min": 0.0005877865855996381, "max": 0.009045908642764408, "count": 5 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.006465652441596019, "min": 0.00532774068794121, "max": 0.06332136049935086, "count": 5 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00028655179539182723, "min": 0.00028655179539182723, "max": 0.00029838354339596195, "count": 5 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0031520697493100996, "min": 0.0020691136102954665, "max": 0.0031520697493100996, "count": 5 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19551726363636365, "min": 0.19551726363636365, "max": 0.19946118095238097, "count": 5 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1506899, "min": 1.3897045333333333, "max": 2.1506899, "count": 5 }, "Pyramids.Policy.Beta.mean": { "value": 0.009552174637272728, "min": 0.009552174637272728, "max": 0.009946171977142856, "count": 5 }, "Pyramids.Policy.Beta.sum": { "value": 0.10507392101, "min": 0.06897148288, "max": 0.10507392101, "count": 5 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0687025710940361, "min": 0.0687025710940361, "max": 0.45670634508132935, "count": 5 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.7557282447814941, "min": 0.7099942564964294, "max": 3.19694447517395, "count": 5 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 996.15625, "min": 984.40625, "max": 999.0, "count": 5 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31877.0, "min": 15984.0, "max": 31968.0, "count": 5 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9346125507727265, "min": -1.0000000521540642, "max": -0.9228750506881624, "count": 5 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -29.90760162472725, "min": -32.000001668930054, "max": -16.000000834465027, "count": 5 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9346125507727265, "min": -1.0000000521540642, "max": -0.9228750506881624, "count": 5 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -29.90760162472725, "min": -32.000001668930054, "max": -16.000000834465027, "count": 5 }, "Pyramids.Policy.RndReward.mean": { "value": 0.7536459516268224, "min": 0.7536459516268224, "max": 8.610899567604065, "count": 5 }, "Pyramids.Policy.RndReward.sum": { "value": 24.116670452058315, "min": 24.116670452058315, "max": 137.77439308166504, "count": 5 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1748528443", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748528788" }, "total": 344.56960941700004, "count": 1, "self": 0.5216151859999627, "children": { "run_training.setup": { "total": 0.021093043000064426, "count": 1, "self": 0.021093043000064426 }, "TrainerController.start_learning": { "total": 344.026901188, "count": 1, "self": 0.2570713980030632, "children": { "TrainerController._reset_env": { "total": 2.447821465000061, "count": 1, "self": 2.447821465000061 }, "TrainerController.advance": { "total": 340.9616144319971, "count": 9783, "self": 0.28863897802102656, "children": { "env_step": { "total": 228.421792245995, "count": 9783, "self": 200.272148808986, "children": { "SubprocessEnvManager._take_step": { "total": 28.000657919996, "count": 9783, "self": 0.8493236969950431, "children": { "TorchPolicy.evaluate": { "total": 27.15133422300096, "count": 9781, "self": 27.15133422300096 } } }, "workers": { "total": 0.14898551701298857, "count": 9782, "self": 0.0, "children": { "worker_root": { "total": 342.82997307999176, "count": 9782, "is_parallel": true, "self": 162.237793356976, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021176360000936256, "count": 1, "is_parallel": true, "self": 0.0006946779999452701, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014229580001483555, "count": 8, "is_parallel": true, "self": 0.0014229580001483555 } } }, "UnityEnvironment.step": { "total": 0.05272724099995685, "count": 1, "is_parallel": true, "self": 0.0006332640000437095, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005856350001067767, "count": 1, "is_parallel": true, "self": 0.0005856350001067767 }, "communicator.exchange": { "total": 0.04968257099994844, "count": 1, "is_parallel": true, "self": 0.04968257099994844 }, "steps_from_proto": { "total": 0.001825770999857923, "count": 1, "is_parallel": true, "self": 0.0004133489997002471, "children": { "_process_rank_one_or_two_observation": { "total": 0.001412422000157676, "count": 8, "is_parallel": true, "self": 0.001412422000157676 } } } } } } }, "UnityEnvironment.step": { "total": 180.59217972301576, "count": 9781, "is_parallel": true, "self": 5.447545174037259, "children": { "UnityEnvironment._generate_step_input": { "total": 4.101706276997675, "count": 9781, "is_parallel": true, "self": 4.101706276997675 }, "communicator.exchange": { "total": 154.1020959519915, "count": 9781, "is_parallel": true, "self": 154.1020959519915 }, "steps_from_proto": { "total": 16.94083231998934, "count": 9781, "is_parallel": true, "self": 3.5175229909548307, "children": { "_process_rank_one_or_two_observation": { "total": 13.42330932903451, "count": 78248, "is_parallel": true, "self": 13.42330932903451 } } } } } } } } } } }, "trainer_advance": { "total": 112.25118320798106, "count": 9782, "self": 0.3296399020075569, "children": { "process_trajectory": { "total": 21.554079229972558, "count": 9782, "self": 21.554079229972558 }, "_update_policy": { "total": 90.36746407600094, "count": 43, "self": 50.6577351279966, "children": { "TorchPPOOptimizer.update": { "total": 39.70972894800434, "count": 3597, "self": 39.70972894800434 } } } } } } }, "trainer_threads": { "total": 1.2549999155453406e-06, "count": 1, "self": 1.2549999155453406e-06 }, "TrainerController._save_models": { "total": 0.36039263799989385, "count": 1, "self": 0.0037798139999267732, "children": { "RLTrainer._checkpoint": { "total": 0.3566128239999671, "count": 1, "self": 0.3566128239999671 } } } } } } }