{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47822296619415283, "min": 0.38711053133010864, "max": 1.4194719791412354, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14316.0830078125, "min": 11557.572265625, "max": 43061.1015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.21990154683589935, "min": -0.17022055387496948, "max": 0.2633354067802429, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 55.63508987426758, "min": -40.34226989746094, "max": 68.46720886230469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.8864403367042542, "min": -0.8864403367042542, "max": 0.35417696833610535, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -224.2694091796875, "min": -224.2694091796875, "max": 85.71082305908203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07116634851194074, "min": 0.06472399017989769, "max": 0.07282879728225847, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9963288791671705, "min": 0.5023583531268971, "max": 1.092431959233877, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.1822836324156794, "min": 0.0006305802573615309, "max": 0.1822836324156794, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 2.551970853819512, "min": 0.008828123603061433, "max": 2.551970853819512, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.37647611263571e-06, "min": 7.37647611263571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010327066557689994, "min": 0.00010327066557689994, "max": 0.0036091341969553, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245879285714285, "min": 0.10245879285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344230999999998, "min": 1.3886848, "max": 2.5696692000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002556334064285713, "min": 0.0002556334064285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035788676899999984, "min": 0.0035788676899999984, "max": 0.12031416553000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01144364383071661, "min": 0.010052837431430817, "max": 0.48294416069984436, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1602110117673874, "min": 0.14073972404003143, "max": 3.3806090354919434, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 623.5510204081633, "min": 522.1296296296297, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30554.0, "min": 15984.0, "max": 33253.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8048856811864036, "min": -1.0000000521540642, "max": 1.0820290599356999, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 39.439398378133774, "min": -30.273201622068882, "max": 63.79859830439091, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8048856811864036, "min": -1.0000000521540642, "max": 1.0820290599356999, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 39.439398378133774, "min": -30.273201622068882, "max": 63.79859830439091, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07171139016638187, "min": 0.06554952464454497, "max": 9.08528567943722, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5138581181527115, "min": 3.3712199871079065, "max": 145.36457087099552, "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": "1711370830", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/tung491/env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1 --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": "1711372944" }, "total": 2114.196695728, "count": 1, "self": 0.3704457110002295, "children": { "run_training.setup": { "total": 0.01752910300001531, "count": 1, "self": 0.01752910300001531 }, "TrainerController.start_learning": { "total": 2113.808720914, "count": 1, "self": 1.3554383020195928, "children": { "TrainerController._reset_env": { "total": 4.6445250249998935, "count": 1, "self": 4.6445250249998935 }, "TrainerController.advance": { "total": 2107.7329056849803, "count": 63458, "self": 1.3103259979125141, "children": { "env_step": { "total": 1253.326523833032, "count": 63458, "self": 1022.5726646679891, "children": { "SubprocessEnvManager._take_step": { "total": 229.88777125997217, "count": 63458, "self": 4.940127104963494, "children": { "TorchPolicy.evaluate": { "total": 224.94764415500867, "count": 62567, "self": 224.94764415500867 } } }, "workers": { "total": 0.866087905070799, "count": 63458, "self": 0.0, "children": { "worker_root": { "total": 2110.8223348129527, "count": 63458, "is_parallel": true, "self": 1182.8103447539456, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020514999998795247, "count": 1, "is_parallel": true, "self": 0.0011021000000255299, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009493999998539948, "count": 8, "is_parallel": true, "self": 0.0009493999998539948 } } }, "UnityEnvironment.step": { "total": 0.03209880500003237, "count": 1, "is_parallel": true, "self": 0.0002471999996487284, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002344000001812674, "count": 1, "is_parallel": true, "self": 0.0002344000001812674 }, "communicator.exchange": { "total": 0.030760005000047386, "count": 1, "is_parallel": true, "self": 0.030760005000047386 }, "steps_from_proto": { "total": 0.0008572000001549895, "count": 1, "is_parallel": true, "self": 0.00023239999995894323, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006248000001960463, "count": 8, "is_parallel": true, "self": 0.0006248000001960463 } } } } } } }, "UnityEnvironment.step": { "total": 928.0119900590071, "count": 63457, "is_parallel": true, "self": 16.010251934043026, "children": { "UnityEnvironment._generate_step_input": { "total": 12.555226317939287, "count": 63457, "is_parallel": true, "self": 12.555226317939287 }, "communicator.exchange": { "total": 849.4656363850502, "count": 63457, "is_parallel": true, "self": 849.4656363850502 }, "steps_from_proto": { "total": 49.98087542197459, "count": 63457, "is_parallel": true, "self": 12.850171524971756, "children": { "_process_rank_one_or_two_observation": { "total": 37.13070389700283, "count": 507656, "is_parallel": true, "self": 37.13070389700283 } } } } } } } } } } }, "trainer_advance": { "total": 853.0960558540355, "count": 63458, "self": 2.607850197067819, "children": { "process_trajectory": { "total": 127.66161222496635, "count": 63458, "self": 127.452523821966, "children": { "RLTrainer._checkpoint": { "total": 0.2090884030003508, "count": 2, "self": 0.2090884030003508 } } }, "_update_policy": { "total": 722.8265934320013, "count": 451, "self": 296.4367549840033, "children": { "TorchPPOOptimizer.update": { "total": 426.38983844799805, "count": 22773, "self": 426.38983844799805 } } } } } } }, "trainer_threads": { "total": 9.000000318337698e-07, "count": 1, "self": 9.000000318337698e-07 }, "TrainerController._save_models": { "total": 0.0758510020000358, "count": 1, "self": 0.0009024000000863452, "children": { "RLTrainer._checkpoint": { "total": 0.07494860199994946, "count": 1, "self": 0.07494860199994946 } } } } } } }