{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.22443263232707977, "min": 0.22443263232707977, "max": 1.4452108144760132, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6715.0244140625, "min": 6715.0244140625, "max": 43841.9140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4140409529209137, "min": -0.1267271190881729, "max": 0.43606990575790405, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.54893493652344, "min": -30.414508819580078, "max": 116.86673736572266, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02705603837966919, "min": 0.011791174300014973, "max": 0.42061206698417664, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.223962306976318, "min": 3.0657052993774414, "max": 99.68505859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06734301679812017, "min": 0.06440833339487047, "max": 0.0740668283639631, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9428022351736824, "min": 0.4957909714479076, "max": 1.0760551788250676, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01351434648088235, "min": 0.0009080456343357838, "max": 0.014139021000142029, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1892008507323529, "min": 0.007500891106215493, "max": 0.2035820501187118, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.34604755135e-06, "min": 7.34604755135e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001028446657189, "min": 0.0001028446657189, "max": 0.0035081243306252993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244865, "min": 0.10244865, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342811, "min": 1.3691136000000002, "max": 2.5693747, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000254620135, "min": 0.000254620135, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00356468189, "min": 0.00356468189, "max": 0.11696053253, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013601607643067837, "min": 0.013601607643067837, "max": 0.6497883200645447, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19042250514030457, "min": 0.19042250514030457, "max": 4.548518180847168, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 440.7323943661972, "min": 400.45205479452056, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31292.0, "min": 15984.0, "max": 33099.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3056788567296216, "min": -1.0000000521540642, "max": 1.4857264433932655, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 92.70319882780313, "min": -32.000001668930054, "max": 101.21799810230732, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3056788567296216, "min": -1.0000000521540642, "max": 1.4857264433932655, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 92.70319882780313, "min": -32.000001668930054, "max": 101.21799810230732, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06145553646976469, "min": 0.06032499827819669, "max": 13.180881757289171, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.363343089353293, "min": 4.343399876030162, "max": 210.89410811662674, "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": "1714515023", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714517107" }, "total": 2084.0014059, "count": 1, "self": 0.4763103139998748, "children": { "run_training.setup": { "total": 0.04919140500010144, "count": 1, "self": 0.04919140500010144 }, "TrainerController.start_learning": { "total": 2083.4759041810003, "count": 1, "self": 1.3374007870274909, "children": { "TrainerController._reset_env": { "total": 2.0459372929999518, "count": 1, "self": 2.0459372929999518 }, "TrainerController.advance": { "total": 2080.0071624629727, "count": 63692, "self": 1.36601219193426, "children": { "env_step": { "total": 1466.2885108930568, "count": 63692, "self": 1340.0996315971017, "children": { "SubprocessEnvManager._take_step": { "total": 125.38840361397615, "count": 63692, "self": 4.6260038560242265, "children": { "TorchPolicy.evaluate": { "total": 120.76239975795193, "count": 62559, "self": 120.76239975795193 } } }, "workers": { "total": 0.8004756819789236, "count": 63692, "self": 0.0, "children": { "worker_root": { "total": 2078.342608572015, "count": 63692, "is_parallel": true, "self": 856.7287022749947, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022580269999252778, "count": 1, "is_parallel": true, "self": 0.0006976099996336416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015604170002916362, "count": 8, "is_parallel": true, "self": 0.0015604170002916362 } } }, "UnityEnvironment.step": { "total": 0.048357051000039064, "count": 1, "is_parallel": true, "self": 0.0006395240000074409, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004436809999788238, "count": 1, "is_parallel": true, "self": 0.0004436809999788238 }, "communicator.exchange": { "total": 0.045484511000040584, "count": 1, "is_parallel": true, "self": 0.045484511000040584 }, "steps_from_proto": { "total": 0.0017893350000122155, "count": 1, "is_parallel": true, "self": 0.0003567120002117008, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014326229998005147, "count": 8, "is_parallel": true, "self": 0.0014326229998005147 } } } } } } }, "UnityEnvironment.step": { "total": 1221.61390629702, "count": 63691, "is_parallel": true, "self": 33.4063720679444, "children": { "UnityEnvironment._generate_step_input": { "total": 23.982455977975405, "count": 63691, "is_parallel": true, "self": 23.982455977975405 }, "communicator.exchange": { "total": 1064.660381192047, "count": 63691, "is_parallel": true, "self": 1064.660381192047 }, "steps_from_proto": { "total": 99.56469705905329, "count": 63691, "is_parallel": true, "self": 20.037477693065057, "children": { "_process_rank_one_or_two_observation": { "total": 79.52721936598823, "count": 509528, "is_parallel": true, "self": 79.52721936598823 } } } } } } } } } } }, "trainer_advance": { "total": 612.3526393779816, "count": 63692, "self": 2.4960276149190577, "children": { "process_trajectory": { "total": 125.8476752730603, "count": 63692, "self": 125.65264659106015, "children": { "RLTrainer._checkpoint": { "total": 0.19502868200015655, "count": 2, "self": 0.19502868200015655 } } }, "_update_policy": { "total": 484.00893649000227, "count": 450, "self": 286.2722688280194, "children": { "TorchPPOOptimizer.update": { "total": 197.7366676619829, "count": 22806, "self": 197.7366676619829 } } } } } } }, "trainer_threads": { "total": 1.4510001165035646e-06, "count": 1, "self": 1.4510001165035646e-06 }, "TrainerController._save_models": { "total": 0.08540218699999969, "count": 1, "self": 0.0013768520002486184, "children": { "RLTrainer._checkpoint": { "total": 0.08402533499975107, "count": 1, "self": 0.08402533499975107 } } } } } } }