{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2178608626127243, "min": 0.2089102417230606, "max": 1.3913394212722778, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6514.9111328125, "min": 6314.10302734375, "max": 42207.671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6457516551017761, "min": -0.07314863055944443, "max": 0.6649767160415649, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.10195922851562, "min": -17.628820419311523, "max": 188.8533935546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011693883687257767, "min": -0.0015647447435185313, "max": 0.27065181732177734, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.297675132751465, "min": -0.4349990487098694, "max": 64.50035858154297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06814360083635188, "min": 0.06661233626142522, "max": 0.07452236115145029, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9540104117089262, "min": 0.509838995385424, "max": 1.0732528871837226, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016412826435130444, "min": 0.0012507676959355762, "max": 0.017720301168516188, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22977957009182623, "min": 0.013319398905371172, "max": 0.24808421635922664, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4085332448071455e-06, "min": 7.4085332448071455e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010371946542730004, "min": 0.00010371946542730004, "max": 0.0037579399473533994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246947857142856, "min": 0.10246947857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345727, "min": 1.3886848, "max": 2.6526466, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002567009092857144, "min": 0.0002567009092857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003593812730000001, "min": 0.003593812730000001, "max": 0.12527939534000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012457561679184437, "min": 0.012172956950962543, "max": 0.4141850471496582, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17440585792064667, "min": 0.17440585792064667, "max": 2.8992953300476074, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.97938144329896, "min": 279.94174757281553, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28613.0, "min": 15984.0, "max": 33971.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6637711133231823, "min": -1.0000000521540642, "max": 1.6992538330646663, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 161.38579799234867, "min": -27.81880161911249, "max": 176.72239863872528, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6637711133231823, "min": -1.0000000521540642, "max": 1.6992538330646663, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 161.38579799234867, "min": -27.81880161911249, "max": 176.72239863872528, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03800263856768671, "min": 0.03558508694438318, "max": 8.074447041377425, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6862559410656104, "min": 3.6862559410656104, "max": 129.1911526620388, "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": "1729844514", "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=PyramidsTraining1 --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": "1729846944" }, "total": 2429.845569266, "count": 1, "self": 0.47735549899971375, "children": { "run_training.setup": { "total": 0.053862128999980996, "count": 1, "self": 0.053862128999980996 }, "TrainerController.start_learning": { "total": 2429.314351638, "count": 1, "self": 1.4114136349717228, "children": { "TrainerController._reset_env": { "total": 6.106251036000003, "count": 1, "self": 6.106251036000003 }, "TrainerController.advance": { "total": 2421.692463269029, "count": 64158, "self": 1.428269589010597, "children": { "env_step": { "total": 1669.0537683600114, "count": 64158, "self": 1502.1591891380945, "children": { "SubprocessEnvManager._take_step": { "total": 166.06582740194665, "count": 64158, "self": 4.73694529690863, "children": { "TorchPolicy.evaluate": { "total": 161.32888210503802, "count": 62562, "self": 161.32888210503802 } } }, "workers": { "total": 0.8287518199703072, "count": 64158, "self": 0.0, "children": { "worker_root": { "total": 2423.881590644007, "count": 64158, "is_parallel": true, "self": 1042.7871329410248, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002103437000073427, "count": 1, "is_parallel": true, "self": 0.000673021000125118, "children": { "_process_rank_one_or_two_observation": { "total": 0.001430415999948309, "count": 8, "is_parallel": true, "self": 0.001430415999948309 } } }, "UnityEnvironment.step": { "total": 0.04922925599998962, "count": 1, "is_parallel": true, "self": 0.0006232499998759522, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004381790000707042, "count": 1, "is_parallel": true, "self": 0.0004381790000707042 }, "communicator.exchange": { "total": 0.04649763800000528, "count": 1, "is_parallel": true, "self": 0.04649763800000528 }, "steps_from_proto": { "total": 0.0016701890000376807, "count": 1, "is_parallel": true, "self": 0.00037701399969591876, "children": { "_process_rank_one_or_two_observation": { "total": 0.001293175000341762, "count": 8, "is_parallel": true, "self": 0.001293175000341762 } } } } } } }, "UnityEnvironment.step": { "total": 1381.094457702982, "count": 64157, "is_parallel": true, "self": 33.18816328195339, "children": { "UnityEnvironment._generate_step_input": { "total": 22.912418710025122, "count": 64157, "is_parallel": true, "self": 22.912418710025122 }, "communicator.exchange": { "total": 1226.0896836820461, "count": 64157, "is_parallel": true, "self": 1226.0896836820461 }, "steps_from_proto": { "total": 98.90419202895737, "count": 64157, "is_parallel": true, "self": 20.525566321235146, "children": { "_process_rank_one_or_two_observation": { "total": 78.37862570772222, "count": 513256, "is_parallel": true, "self": 78.37862570772222 } } } } } } } } } } }, "trainer_advance": { "total": 751.2104253200071, "count": 64158, "self": 2.8918697650162812, "children": { "process_trajectory": { "total": 140.04193731999248, "count": 64158, "self": 139.74784854999234, "children": { "RLTrainer._checkpoint": { "total": 0.294088770000144, "count": 2, "self": 0.294088770000144 } } }, "_update_policy": { "total": 608.2766182349983, "count": 459, "self": 313.0003535959776, "children": { "TorchPPOOptimizer.update": { "total": 295.2762646390207, "count": 22794, "self": 295.2762646390207 } } } } } } }, "trainer_threads": { "total": 8.090000847005285e-07, "count": 1, "self": 8.090000847005285e-07 }, "TrainerController._save_models": { "total": 0.1042228889996295, "count": 1, "self": 0.0014271189993451117, "children": { "RLTrainer._checkpoint": { "total": 0.10279577000028439, "count": 1, "self": 0.10279577000028439 } } } } } } }