{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4460033178329468, "min": 0.4460033178329468, "max": 1.4870394468307495, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13408.6435546875, "min": 13333.6787109375, "max": 45110.828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.514739453792572, "min": -0.10502833127975464, "max": 0.6126740574836731, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.5533447265625, "min": -25.31182861328125, "max": 171.54873657226562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026935959234833717, "min": -0.0023613020312041044, "max": 0.2371523231267929, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.407388687133789, "min": -0.6304676532745361, "max": 56.205101013183594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06952079055675617, "min": 0.06536565200753082, "max": 0.07343824240489907, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0428118583513426, "min": 0.5039396368791068, "max": 1.0428118583513426, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01538306740960989, "min": 0.0009021139529355517, "max": 0.015875947643151308, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23074601114414833, "min": 0.00778844243024295, "max": 0.23074601114414833, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.473117508993337e-06, "min": 7.473117508993337e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011209676263490005, "min": 0.00011209676263490005, "max": 0.0033704371765209996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249100666666669, "min": 0.10249100666666669, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373651000000004, "min": 1.3691136000000002, "max": 2.4859925, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002588515660000001, "min": 0.0002588515660000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003882773490000002, "min": 0.003882773490000002, "max": 0.11236555209999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008728018030524254, "min": 0.00865101721137762, "max": 0.3481988310813904, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13092027604579926, "min": 0.12111424654722214, "max": 2.437391757965088, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 367.0, "min": 318.36559139784947, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29727.0, "min": 15984.0, "max": 32469.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.50950614730885, "min": -1.0000000521540642, "max": 1.638606423732414, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.26999793201685, "min": -32.000001668930054, "max": 152.3903974071145, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.50950614730885, "min": -1.0000000521540642, "max": 1.638606423732414, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.26999793201685, "min": -32.000001668930054, "max": 152.3903974071145, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033139266038851034, "min": 0.029304648285120805, "max": 7.925859946757555, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6842805491469335, "min": 2.6842805491469335, "max": 126.81375914812088, "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": "1723578756", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723580949" }, "total": 2193.0775722119997, "count": 1, "self": 0.4759979679997741, "children": { "run_training.setup": { "total": 0.05479584900012924, "count": 1, "self": 0.05479584900012924 }, "TrainerController.start_learning": { "total": 2192.546778395, "count": 1, "self": 1.5606907079722987, "children": { "TrainerController._reset_env": { "total": 2.2281223959998897, "count": 1, "self": 2.2281223959998897 }, "TrainerController.advance": { "total": 2188.6659204570283, "count": 63778, "self": 1.6263752930703959, "children": { "env_step": { "total": 1548.8701120480005, "count": 63778, "self": 1411.3661364520403, "children": { "SubprocessEnvManager._take_step": { "total": 136.59618666498818, "count": 63778, "self": 4.786842260096819, "children": { "TorchPolicy.evaluate": { "total": 131.80934440489136, "count": 62569, "self": 131.80934440489136 } } }, "workers": { "total": 0.9077889309719467, "count": 63778, "self": 0.0, "children": { "worker_root": { "total": 2187.7212983169375, "count": 63778, "is_parallel": true, "self": 901.4499792629858, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020993449998059077, "count": 1, "is_parallel": true, "self": 0.0006466289992204111, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014527160005854967, "count": 8, "is_parallel": true, "self": 0.0014527160005854967 } } }, "UnityEnvironment.step": { "total": 0.047042229999988194, "count": 1, "is_parallel": true, "self": 0.0006311990005087864, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005055679998804408, "count": 1, "is_parallel": true, "self": 0.0005055679998804408 }, "communicator.exchange": { "total": 0.04422179799985315, "count": 1, "is_parallel": true, "self": 0.04422179799985315 }, "steps_from_proto": { "total": 0.0016836649997458153, "count": 1, "is_parallel": true, "self": 0.00035854199950335897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013251230002424563, "count": 8, "is_parallel": true, "self": 0.0013251230002424563 } } } } } } }, "UnityEnvironment.step": { "total": 1286.2713190539516, "count": 63777, "is_parallel": true, "self": 34.199052577957445, "children": { "UnityEnvironment._generate_step_input": { "total": 22.713499207005498, "count": 63777, "is_parallel": true, "self": 22.713499207005498 }, "communicator.exchange": { "total": 1130.80936440802, "count": 63777, "is_parallel": true, "self": 1130.80936440802 }, "steps_from_proto": { "total": 98.54940286096871, "count": 63777, "is_parallel": true, "self": 20.032001392820348, "children": { "_process_rank_one_or_two_observation": { "total": 78.51740146814836, "count": 510216, "is_parallel": true, "self": 78.51740146814836 } } } } } } } } } } }, "trainer_advance": { "total": 638.1694331159574, "count": 63778, "self": 2.82888868206237, "children": { "process_trajectory": { "total": 127.83728608689671, "count": 63778, "self": 127.63983267689628, "children": { "RLTrainer._checkpoint": { "total": 0.19745341000043481, "count": 2, "self": 0.19745341000043481 } } }, "_update_policy": { "total": 507.50325834699834, "count": 447, "self": 299.7677595690152, "children": { "TorchPPOOptimizer.update": { "total": 207.73549877798314, "count": 22818, "self": 207.73549877798314 } } } } } } }, "trainer_threads": { "total": 9.549994501867332e-07, "count": 1, "self": 9.549994501867332e-07 }, "TrainerController._save_models": { "total": 0.09204387899990252, "count": 1, "self": 0.0015893419995336444, "children": { "RLTrainer._checkpoint": { "total": 0.09045453700036887, "count": 1, "self": 0.09045453700036887 } } } } } } }