{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4520981013774872, "min": 0.4385925531387329, "max": 1.4240314960479736, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13562.943359375, "min": 13234.96875, "max": 43199.41796875, "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": 0.567078173160553, "min": -0.0839814692735672, "max": 0.6284586787223816, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.91604614257812, "min": -20.15555191040039, "max": 181.6245574951172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015149444341659546, "min": 0.010907419957220554, "max": 0.29972711205482483, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.272143363952637, "min": 2.737762451171875, "max": 71.03532409667969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06782779156665561, "min": 0.06538783962536225, "max": 0.07321812053791965, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9495890819331786, "min": 0.5020767523982059, "max": 1.0757871098612668, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015012845410854512, "min": 0.0005337108905319672, "max": 0.018148661517660092, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21017983575196317, "min": 0.007471952467447542, "max": 0.2540812612472413, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.379304683121427e-06, "min": 7.379304683121427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010331026556369998, "min": 0.00010331026556369998, "max": 0.0036338686887105, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245973571428571, "min": 0.10245973571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344363, "min": 1.3886848, "max": 2.6112895000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002557275978571427, "min": 0.0002557275978571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035801863699999985, "min": 0.0035801863699999985, "max": 0.12114782104999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011117576621472836, "min": 0.011117576621472836, "max": 0.3719063401222229, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15564607083797455, "min": 0.15564607083797455, "max": 2.603344440460205, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 334.27659574468083, "min": 287.59574468085106, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31422.0, "min": 15984.0, "max": 34009.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.580589337314063, "min": -1.0000000521540642, "max": 1.7124042452332822, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.57539770752192, "min": -28.434001624584198, "max": 175.67799868434668, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.580589337314063, "min": -1.0000000521540642, "max": 1.7124042452332822, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.57539770752192, "min": -28.434001624584198, "max": 175.67799868434668, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03858262377988022, "min": 0.03573600412044548, "max": 7.6225122809410095, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6267666353087407, "min": 3.359184387321875, "max": 121.96019649505615, "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": "1691031911", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691034142" }, "total": 2230.8828622930005, "count": 1, "self": 0.47835774399982256, "children": { "run_training.setup": { "total": 0.038629620000392606, "count": 1, "self": 0.038629620000392606 }, "TrainerController.start_learning": { "total": 2230.3658749290003, "count": 1, "self": 1.3760239819612252, "children": { "TrainerController._reset_env": { "total": 5.090157269999963, "count": 1, "self": 5.090157269999963 }, "TrainerController.advance": { "total": 2223.753318108039, "count": 63821, "self": 1.404763570048999, "children": { "env_step": { "total": 1525.4432089920551, "count": 63821, "self": 1410.897777992062, "children": { "SubprocessEnvManager._take_step": { "total": 113.70518299204286, "count": 63821, "self": 4.754622320024282, "children": { "TorchPolicy.evaluate": { "total": 108.95056067201858, "count": 62560, "self": 108.95056067201858 } } }, "workers": { "total": 0.8402480079503221, "count": 63821, "self": 0.0, "children": { "worker_root": { "total": 2225.088243591005, "count": 63821, "is_parallel": true, "self": 930.3355124699915, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00204060899977776, "count": 1, "is_parallel": true, "self": 0.0006841119998171052, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013564969999606546, "count": 8, "is_parallel": true, "self": 0.0013564969999606546 } } }, "UnityEnvironment.step": { "total": 0.0819356830002107, "count": 1, "is_parallel": true, "self": 0.0007139480003388599, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006495170000562211, "count": 1, "is_parallel": true, "self": 0.0006495170000562211 }, "communicator.exchange": { "total": 0.07853370800012272, "count": 1, "is_parallel": true, "self": 0.07853370800012272 }, "steps_from_proto": { "total": 0.0020385099996929057, "count": 1, "is_parallel": true, "self": 0.0004219940001348732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016165159995580325, "count": 8, "is_parallel": true, "self": 0.0016165159995580325 } } } } } } }, "UnityEnvironment.step": { "total": 1294.7527311210133, "count": 63820, "is_parallel": true, "self": 33.91242439177995, "children": { "UnityEnvironment._generate_step_input": { "total": 24.63959133308572, "count": 63820, "is_parallel": true, "self": 24.63959133308572 }, "communicator.exchange": { "total": 1131.0344022560848, "count": 63820, "is_parallel": true, "self": 1131.0344022560848 }, "steps_from_proto": { "total": 105.16631314006281, "count": 63820, "is_parallel": true, "self": 21.043666498122548, "children": { "_process_rank_one_or_two_observation": { "total": 84.12264664194026, "count": 510560, "is_parallel": true, "self": 84.12264664194026 } } } } } } } } } } }, "trainer_advance": { "total": 696.9053455459348, "count": 63821, "self": 2.609846612835554, "children": { "process_trajectory": { "total": 114.05584478109131, "count": 63821, "self": 113.79595242509095, "children": { "RLTrainer._checkpoint": { "total": 0.2598923560003641, "count": 2, "self": 0.2598923560003641 } } }, "_update_policy": { "total": 580.2396541520079, "count": 455, "self": 376.82433186496974, "children": { "TorchPPOOptimizer.update": { "total": 203.41532228703818, "count": 22788, "self": 203.41532228703818 } } } } } } }, "trainer_threads": { "total": 1.1940001058974303e-06, "count": 1, "self": 1.1940001058974303e-06 }, "TrainerController._save_models": { "total": 0.14637437500005035, "count": 1, "self": 0.0019303560002299491, "children": { "RLTrainer._checkpoint": { "total": 0.1444440189998204, "count": 1, "self": 0.1444440189998204 } } } } } } }