{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4920957088470459, "min": 0.4890662729740143, "max": 1.3875353336334229, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14770.7451171875, "min": 14770.7451171875, "max": 42092.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5041217803955078, "min": -0.18171775341033936, "max": 0.5752589106559753, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.12112426757812, "min": -43.067108154296875, "max": 159.3467254638672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0022002020850777626, "min": -0.06886011362075806, "max": 0.46801960468292236, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5984549522399902, "min": -18.17906951904297, "max": 110.92064666748047, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06906653762238824, "min": 0.06533463780734954, "max": 0.07335392008781765, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0359980643358235, "min": 0.49289109043465207, "max": 1.0454800486849207, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016061405007106563, "min": 0.00014500886668961116, "max": 0.016920334618286386, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24092107510659844, "min": 0.002030124133654556, "max": 0.24092107510659844, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.530397489899996e-06, "min": 7.530397489899996e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011295596234849994, "min": 0.00011295596234849994, "max": 0.003509026130324699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025101, "min": 0.1025101, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376515000000002, "min": 1.3886848, "max": 2.5696753000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002607589899999999, "min": 0.0002607589899999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003911384849999998, "min": 0.003911384849999998, "max": 0.11699056246999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010746660642325878, "min": 0.010656860657036304, "max": 0.5910816788673401, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1611999124288559, "min": 0.14919604361057281, "max": 4.137571811676025, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 385.9620253164557, "min": 339.7560975609756, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30491.0, "min": 15984.0, "max": 33280.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5380632595359525, "min": -1.0000000521540642, "max": 1.6119951629135982, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 121.50699750334024, "min": -29.82260162383318, "max": 133.79559852182865, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5380632595359525, "min": -1.0000000521540642, "max": 1.6119951629135982, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 121.50699750334024, "min": -29.82260162383318, "max": 133.79559852182865, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042848783572457874, "min": 0.037850367200577696, "max": 12.331308932974935, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.385053902224172, "min": 3.097138458455447, "max": 197.30094292759895, "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": "1682430486", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1682432519" }, "total": 2032.9653231450002, "count": 1, "self": 0.424309299000015, "children": { "run_training.setup": { "total": 0.10965862800003379, "count": 1, "self": 0.10965862800003379 }, "TrainerController.start_learning": { "total": 2032.4313552180001, "count": 1, "self": 1.3089308629832885, "children": { "TrainerController._reset_env": { "total": 3.797527674000321, "count": 1, "self": 3.797527674000321 }, "TrainerController.advance": { "total": 2027.230148288017, "count": 63712, "self": 1.3702787461820662, "children": { "env_step": { "total": 1432.727591951962, "count": 63712, "self": 1330.2347005090878, "children": { "SubprocessEnvManager._take_step": { "total": 101.65839286989649, "count": 63712, "self": 4.637798856894733, "children": { "TorchPolicy.evaluate": { "total": 97.02059401300176, "count": 62583, "self": 97.02059401300176 } } }, "workers": { "total": 0.8344985729777363, "count": 63712, "self": 0.0, "children": { "worker_root": { "total": 2027.8946715069696, "count": 63712, "is_parallel": true, "self": 804.8608109388633, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016728259997762507, "count": 1, "is_parallel": true, "self": 0.0005280149998725392, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011448109999037115, "count": 8, "is_parallel": true, "self": 0.0011448109999037115 } } }, "UnityEnvironment.step": { "total": 0.04592833599963342, "count": 1, "is_parallel": true, "self": 0.0005309989992383635, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048410399995191256, "count": 1, "is_parallel": true, "self": 0.00048410399995191256 }, "communicator.exchange": { "total": 0.0432517980002558, "count": 1, "is_parallel": true, "self": 0.0432517980002558 }, "steps_from_proto": { "total": 0.001661435000187339, "count": 1, "is_parallel": true, "self": 0.00036200700014887843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012994280000384606, "count": 8, "is_parallel": true, "self": 0.0012994280000384606 } } } } } } }, "UnityEnvironment.step": { "total": 1223.0338605681063, "count": 63711, "is_parallel": true, "self": 31.770937040229455, "children": { "UnityEnvironment._generate_step_input": { "total": 21.826472902949263, "count": 63711, "is_parallel": true, "self": 21.826472902949263 }, "communicator.exchange": { "total": 1075.9577515440315, "count": 63711, "is_parallel": true, "self": 1075.9577515440315 }, "steps_from_proto": { "total": 93.47869908089615, "count": 63711, "is_parallel": true, "self": 19.19604877243637, "children": { "_process_rank_one_or_two_observation": { "total": 74.28265030845978, "count": 509688, "is_parallel": true, "self": 74.28265030845978 } } } } } } } } } } }, "trainer_advance": { "total": 593.132277589873, "count": 63712, "self": 2.4788967978734036, "children": { "process_trajectory": { "total": 102.02779650500543, "count": 63712, "self": 101.8295001370052, "children": { "RLTrainer._checkpoint": { "total": 0.19829636800022854, "count": 2, "self": 0.19829636800022854 } } }, "_update_policy": { "total": 488.6255842869941, "count": 451, "self": 311.2695347919739, "children": { "TorchPPOOptimizer.update": { "total": 177.35604949502022, "count": 22755, "self": 177.35604949502022 } } } } } } }, "trainer_threads": { "total": 1.0579997251625173e-06, "count": 1, "self": 1.0579997251625173e-06 }, "TrainerController._save_models": { "total": 0.09474733499973809, "count": 1, "self": 0.0014030649999767775, "children": { "RLTrainer._checkpoint": { "total": 0.09334426999976131, "count": 1, "self": 0.09334426999976131 } } } } } } }