{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3909001052379608, "min": 0.3909001052379608, "max": 1.4855890274047852, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11783.29296875, "min": 11783.29296875, "max": 45066.828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5218902826309204, "min": -0.0899086520075798, "max": 0.5762224793434143, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.95416259765625, "min": -21.57807731628418, "max": 159.61363220214844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026484861969947815, "min": 0.007223057094961405, "max": 0.21975024044513702, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.203882694244385, "min": 1.863548755645752, "max": 52.080806732177734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06519688296427557, "min": 0.06308527765495218, "max": 0.07349047087485891, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.912756361499858, "min": 0.4915454067480845, "max": 1.0505856757129854, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014720595594431457, "min": 0.00039921790524475307, "max": 0.01597288504094144, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2060883383220404, "min": 0.004391396957692284, "max": 0.2395932756141216, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.680590296978574e-06, "min": 7.680590296978574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010752826415770005, "min": 0.00010752826415770005, "max": 0.0032565428144858, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256016428571428, "min": 0.10256016428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358423, "min": 1.3886848, "max": 2.4015169, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002657604121428572, "min": 0.0002657604121428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003720645770000001, "min": 0.003720645770000001, "max": 0.10857286858, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01098582986742258, "min": 0.01098582986742258, "max": 0.31344714760780334, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15380162000656128, "min": 0.15380162000656128, "max": 2.1941299438476562, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.85185185185185, "min": 329.85185185185185, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26718.0, "min": 15984.0, "max": 32705.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6701481323919178, "min": -1.0000000521540642, "max": 1.6701481323919178, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.28199872374535, "min": -31.99760165810585, "max": 136.41159902513027, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6701481323919178, "min": -1.0000000521540642, "max": 1.6701481323919178, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.28199872374535, "min": -31.99760165810585, "max": 136.41159902513027, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03768332662254164, "min": 0.03768332662254164, "max": 6.3549231248907745, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0523494564258726, "min": 3.0523494564258726, "max": 101.67876999825239, "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": "1741814301", "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": "1741816554" }, "total": 2252.7693704440003, "count": 1, "self": 0.5262379460004922, "children": { "run_training.setup": { "total": 0.022685464000005595, "count": 1, "self": 0.022685464000005595 }, "TrainerController.start_learning": { "total": 2252.220447034, "count": 1, "self": 1.3657855129531526, "children": { "TrainerController._reset_env": { "total": 2.1039128470001742, "count": 1, "self": 2.1039128470001742 }, "TrainerController.advance": { "total": 2248.6643654440463, "count": 63728, "self": 1.4180772760482796, "children": { "env_step": { "total": 1565.3495101279777, "count": 63728, "self": 1408.892283942851, "children": { "SubprocessEnvManager._take_step": { "total": 155.6694172680468, "count": 63728, "self": 4.676986226921599, "children": { "TorchPolicy.evaluate": { "total": 150.9924310411252, "count": 62554, "self": 150.9924310411252 } } }, "workers": { "total": 0.7878089170799285, "count": 63728, "self": 0.0, "children": { "worker_root": { "total": 2247.186786885985, "count": 63728, "is_parallel": true, "self": 952.5359443430266, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002083723999930953, "count": 1, "is_parallel": true, "self": 0.0007137920006243803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013699319993065728, "count": 8, "is_parallel": true, "self": 0.0013699319993065728 } } }, "UnityEnvironment.step": { "total": 0.050496093000219844, "count": 1, "is_parallel": true, "self": 0.0004994930004613707, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005454959996313846, "count": 1, "is_parallel": true, "self": 0.0005454959996313846 }, "communicator.exchange": { "total": 0.047853393999957916, "count": 1, "is_parallel": true, "self": 0.047853393999957916 }, "steps_from_proto": { "total": 0.0015977100001691724, "count": 1, "is_parallel": true, "self": 0.0003549520001797646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012427579999894078, "count": 8, "is_parallel": true, "self": 0.0012427579999894078 } } } } } } }, "UnityEnvironment.step": { "total": 1294.6508425429583, "count": 63727, "is_parallel": true, "self": 31.538641026957976, "children": { "UnityEnvironment._generate_step_input": { "total": 23.125402466007472, "count": 63727, "is_parallel": true, "self": 23.125402466007472 }, "communicator.exchange": { "total": 1143.695759646013, "count": 63727, "is_parallel": true, "self": 1143.695759646013 }, "steps_from_proto": { "total": 96.29103940398, "count": 63727, "is_parallel": true, "self": 19.660741981884257, "children": { "_process_rank_one_or_two_observation": { "total": 76.63029742209574, "count": 509816, "is_parallel": true, "self": 76.63029742209574 } } } } } } } } } } }, "trainer_advance": { "total": 681.8967780400203, "count": 63728, "self": 2.6906181049362203, "children": { "process_trajectory": { "total": 129.972871375081, "count": 63728, "self": 129.76526415008038, "children": { "RLTrainer._checkpoint": { "total": 0.20760722500062911, "count": 2, "self": 0.20760722500062911 } } }, "_update_policy": { "total": 549.2332885600031, "count": 447, "self": 303.29739391403973, "children": { "TorchPPOOptimizer.update": { "total": 245.93589464596334, "count": 22797, "self": 245.93589464596334 } } } } } } }, "trainer_threads": { "total": 1.0840003596968018e-06, "count": 1, "self": 1.0840003596968018e-06 }, "TrainerController._save_models": { "total": 0.086382145999778, "count": 1, "self": 0.0016159719998540822, "children": { "RLTrainer._checkpoint": { "total": 0.08476617399992392, "count": 1, "self": 0.08476617399992392 } } } } } } }