{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45756399631500244, "min": 0.45756399631500244, "max": 1.5040336847305298, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13609.783203125, "min": 13609.783203125, "max": 45626.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989889.0, "min": 29995.0, "max": 989889.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989889.0, "min": 29995.0, "max": 989889.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4547107219696045, "min": -0.17053431272506714, "max": 0.6123825907707214, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.31718444824219, "min": -40.58716583251953, "max": 173.91665649414062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06040317192673683, "min": -0.013297402299940586, "max": 0.35190609097480774, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.24845314025879, "min": -3.4706220626831055, "max": 83.75364685058594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06661658520183338, "min": 0.06348988306403737, "max": 0.07438346972779232, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9992487780275006, "min": 0.5950677578223386, "max": 1.043722482919168, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014879163227434378, "min": 5.819783857324592e-05, "max": 0.01740750817615273, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22318744841151567, "min": 0.000698374062878951, "max": 0.2437051144661382, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4580375140200035e-06, "min": 7.4580375140200035e-06, "max": 0.0002948495642168125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011187056271030005, "min": 0.00011187056271030005, "max": 0.0031405685531438994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248598, "min": 0.10248598, "max": 0.19828318749999999, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372897, "min": 1.4777525, "max": 2.3593829, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025834940200000013, "min": 0.00025834940200000013, "max": 0.00982849043125, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003875241030000002, "min": 0.003875241030000002, "max": 0.10471092439, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00784855056554079, "min": 0.00784855056554079, "max": 0.4417484700679779, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11772826313972473, "min": 0.11258344352245331, "max": 3.5339877605438232, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 417.14666666666665, "min": 318.6989247311828, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31286.0, "min": 16282.0, "max": 32312.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3482105018276918, "min": -1.0000000521540642, "max": 1.6559318952420925, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 102.46399813890457, "min": -32.000001668930054, "max": 155.6575981527567, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3482105018276918, "min": -1.0000000521540642, "max": 1.6559318952420925, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 102.46399813890457, "min": -32.000001668930054, "max": 155.6575981527567, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033934670875360576, "min": 0.028049252265047567, "max": 9.304248069139089, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.579034986527404, "min": 2.329140003363136, "max": 158.1722171753645, "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": "1742812154", "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": "1742814391" }, "total": 2236.349685046, "count": 1, "self": 0.5372856650001268, "children": { "run_training.setup": { "total": 0.023198602999968898, "count": 1, "self": 0.023198602999968898 }, "TrainerController.start_learning": { "total": 2235.789200778, "count": 1, "self": 1.3817650539635906, "children": { "TrainerController._reset_env": { "total": 3.5499088220000203, "count": 1, "self": 3.5499088220000203 }, "TrainerController.advance": { "total": 2230.7650272690366, "count": 63770, "self": 1.5002949470731437, "children": { "env_step": { "total": 1548.9240599449613, "count": 63770, "self": 1390.443742678909, "children": { "SubprocessEnvManager._take_step": { "total": 157.65761558704367, "count": 63770, "self": 4.900581816033423, "children": { "TorchPolicy.evaluate": { "total": 152.75703377101024, "count": 62567, "self": 152.75703377101024 } } }, "workers": { "total": 0.8227016790086736, "count": 63770, "self": 0.0, "children": { "worker_root": { "total": 2230.734022660008, "count": 63770, "is_parallel": true, "self": 954.912694901981, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005917974999988473, "count": 1, "is_parallel": true, "self": 0.004079378999790606, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018385960001978674, "count": 8, "is_parallel": true, "self": 0.0018385960001978674 } } }, "UnityEnvironment.step": { "total": 0.0524213859999918, "count": 1, "is_parallel": true, "self": 0.0005606560000614991, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005038649999278277, "count": 1, "is_parallel": true, "self": 0.0005038649999278277 }, "communicator.exchange": { "total": 0.04960968499995033, "count": 1, "is_parallel": true, "self": 0.04960968499995033 }, "steps_from_proto": { "total": 0.0017471800000521398, "count": 1, "is_parallel": true, "self": 0.0004916929999581043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012554870000940355, "count": 8, "is_parallel": true, "self": 0.0012554870000940355 } } } } } } }, "UnityEnvironment.step": { "total": 1275.821327758027, "count": 63769, "is_parallel": true, "self": 32.32314335805586, "children": { "UnityEnvironment._generate_step_input": { "total": 23.03877689896126, "count": 63769, "is_parallel": true, "self": 23.03877689896126 }, "communicator.exchange": { "total": 1123.395636481983, "count": 63769, "is_parallel": true, "self": 1123.395636481983 }, "steps_from_proto": { "total": 97.06377101902706, "count": 63769, "is_parallel": true, "self": 19.806728485915414, "children": { "_process_rank_one_or_two_observation": { "total": 77.25704253311164, "count": 510152, "is_parallel": true, "self": 77.25704253311164 } } } } } } } } } } }, "trainer_advance": { "total": 680.3406723770023, "count": 63770, "self": 2.591274365991012, "children": { "process_trajectory": { "total": 130.16705984501073, "count": 63770, "self": 129.83959507201075, "children": { "RLTrainer._checkpoint": { "total": 0.32746477299997423, "count": 2, "self": 0.32746477299997423 } } }, "_update_policy": { "total": 547.5823381660006, "count": 443, "self": 297.358186570994, "children": { "TorchPPOOptimizer.update": { "total": 250.22415159500656, "count": 22827, "self": 250.22415159500656 } } } } } } }, "trainer_threads": { "total": 7.860003279347438e-07, "count": 1, "self": 7.860003279347438e-07 }, "TrainerController._save_models": { "total": 0.0924988469996606, "count": 1, "self": 0.001290584999424027, "children": { "RLTrainer._checkpoint": { "total": 0.09120826200023657, "count": 1, "self": 0.09120826200023657 } } } } } } }