{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2287800908088684, "min": 0.2287800908088684, "max": 1.296623945236206, "count": 48 }, "Pyramids.Policy.Entropy.sum": { "value": 6867.06298828125, "min": 6867.06298828125, "max": 39334.3828125, "count": 48 }, "Pyramids.Step.mean": { "value": 1439936.0, "min": 29952.0, "max": 1439936.0, "count": 48 }, "Pyramids.Step.sum": { "value": 1439936.0, "min": 29952.0, "max": 1439936.0, "count": 48 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7121182680130005, "min": -0.0885230079293251, "max": 0.7318061590194702, "count": 48 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 203.6658172607422, "min": -21.33404541015625, "max": 215.48056030273438, "count": 48 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.001125785754993558, "min": -0.015700027346611023, "max": 0.47521424293518066, "count": 48 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.3219747245311737, "min": -4.443107604980469, "max": 112.62577819824219, "count": 48 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07021538059333801, "min": 0.06505273897762061, "max": 0.0742398063921129, "count": 48 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9830153283067322, "min": 0.5196786447447903, "max": 1.08435721284089, "count": 48 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01282999907500901, "min": 0.0005827243171431567, "max": 0.015978009263303, "count": 48 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17961998705012613, "min": 0.006992691805717881, "max": 0.23931300645926964, "count": 48 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001575045403556452, "min": 0.0001575045403556452, "max": 0.00029838354339596195, "count": 48 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002205063564979033, "min": 0.0020886848037717336, "max": 0.004072742342419266, "count": 48 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1525014976190476, "min": 0.1525014976190476, "max": 0.19946118095238097, "count": 48 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1350209666666666, "min": 1.3962282666666668, "max": 2.857580733333334, "count": 48 }, "Pyramids.Policy.Beta.mean": { "value": 0.005254899612142857, "min": 0.005254899612142857, "max": 0.009946171977142856, "count": 48 }, "Pyramids.Policy.Beta.sum": { "value": 0.07356859456999999, "min": 0.06962320384, "max": 0.13577231526, "count": 48 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008799695409834385, "min": 0.00875086523592472, "max": 0.4917472302913666, "count": 48 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12319573760032654, "min": 0.12251210957765579, "max": 3.442230701446533, "count": 48 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 271.52884615384613, "min": 264.7521367521368, "max": 999.0, "count": 48 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28239.0, "min": 15984.0, "max": 32379.0, "count": 48 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.729114267088118, "min": -1.0000000521540642, "max": 1.7352478477435234, "count": 48 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.5569980442524, "min": -30.32180167734623, "max": 203.02399818599224, "count": 48 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.729114267088118, "min": -1.0000000521540642, "max": 1.7352478477435234, "count": 48 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.5569980442524, "min": -30.32180167734623, "max": 203.02399818599224, "count": 48 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024840027196859453, "min": 0.02464637348492869, "max": 10.164061093702912, "count": 48 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6082028556702426, "min": 2.6082028556702426, "max": 162.6249774992466, "count": 48 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 48 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 48 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739938727", "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": "1739942277" }, "total": 3550.440058499, "count": 1, "self": 0.9131385629993929, "children": { "run_training.setup": { "total": 0.045238568999934614, "count": 1, "self": 0.045238568999934614 }, "TrainerController.start_learning": { "total": 3549.4816813670004, "count": 1, "self": 2.225426468016849, "children": { "TrainerController._reset_env": { "total": 3.7638866949999965, "count": 1, "self": 3.7638866949999965 }, "TrainerController.advance": { "total": 3543.492298655984, "count": 93475, "self": 2.4141350760264686, "children": { "env_step": { "total": 2535.2628630469967, "count": 93475, "self": 2296.648770004984, "children": { "SubprocessEnvManager._take_step": { "total": 237.32950750804048, "count": 93475, "self": 7.200047699025845, "children": { "TorchPolicy.evaluate": { "total": 230.12945980901463, "count": 90699, "self": 230.12945980901463 } } }, "workers": { "total": 1.284585533972404, "count": 93474, "self": 0.0, "children": { "worker_root": { "total": 3541.35744251494, "count": 93474, "is_parallel": true, "self": 1420.2002555739673, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006319818000065425, "count": 1, "is_parallel": true, "self": 0.004307485000254019, "children": { "_process_rank_one_or_two_observation": { "total": 0.002012332999811406, "count": 8, "is_parallel": true, "self": 0.002012332999811406 } } }, "UnityEnvironment.step": { "total": 0.053688636000060797, "count": 1, "is_parallel": true, "self": 0.0005899760001284449, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004806459999144863, "count": 1, "is_parallel": true, "self": 0.0004806459999144863 }, "communicator.exchange": { "total": 0.050745119999987764, "count": 1, "is_parallel": true, "self": 0.050745119999987764 }, "steps_from_proto": { "total": 0.0018728940000301009, "count": 1, "is_parallel": true, "self": 0.0005069990002084523, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013658949998216485, "count": 8, "is_parallel": true, "self": 0.0013658949998216485 } } } } } } }, "UnityEnvironment.step": { "total": 2121.1571869409727, "count": 93473, "is_parallel": true, "self": 49.44527891285088, "children": { "UnityEnvironment._generate_step_input": { "total": 34.61729169706166, "count": 93473, "is_parallel": true, "self": 34.61729169706166 }, "communicator.exchange": { "total": 1890.7361328761153, "count": 93473, "is_parallel": true, "self": 1890.7361328761153 }, "steps_from_proto": { "total": 146.35848345494446, "count": 93473, "is_parallel": true, "self": 30.39459701242231, "children": { "_process_rank_one_or_two_observation": { "total": 115.96388644252215, "count": 747784, "is_parallel": true, "self": 115.96388644252215 } } } } } } } } } } }, "trainer_advance": { "total": 1005.8153005329611, "count": 93474, "self": 4.342725810909087, "children": { "process_trajectory": { "total": 194.66727784505167, "count": 93474, "self": 194.4247313660518, "children": { "RLTrainer._checkpoint": { "total": 0.24254647899988413, "count": 2, "self": 0.24254647899988413 } } }, "_update_policy": { "total": 806.8052968770004, "count": 668, "self": 442.52006966603415, "children": { "TorchPPOOptimizer.update": { "total": 364.28522721096624, "count": 33051, "self": 364.28522721096624 } } } } } } }, "trainer_threads": { "total": 1.2519994925241917e-06, "count": 1, "self": 1.2519994925241917e-06 }, "TrainerController._save_models": { "total": 6.829599988122936e-05, "count": 1, "self": 1.7751999621395953e-05, "children": { "RLTrainer._checkpoint": { "total": 5.054400025983341e-05, "count": 1, "self": 5.054400025983341e-05 } } } } } } }