{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20165009796619415, "min": 0.20165009796619415, "max": 1.4859274625778198, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6081.76708984375, "min": 6081.76708984375, "max": 45077.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47230395674705505, "min": -0.08003924787044525, "max": 0.6197487115859985, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 128.93898010253906, "min": -19.289459228515625, "max": 176.62838745117188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030273353680968285, "min": 0.008243480697274208, "max": 0.3215332329273224, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.264625549316406, "min": 2.2257397174835205, "max": 77.16797637939453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06747374603611546, "min": 0.06566373545224667, "max": 0.07328885045320219, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9446324445056163, "min": 0.4663732707595463, "max": 1.050530262941417, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014956572221774517, "min": 0.0011771320511898028, "max": 0.014992799073679787, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20939201110484323, "min": 0.00823992435832862, "max": 0.20989918703151703, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.487497504200001e-06, "min": 7.487497504200001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010482496505880002, "min": 0.00010482496505880002, "max": 0.0033843893718703, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024958, "min": 0.1024958, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349412, "min": 1.3691136000000002, "max": 2.5281297, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002593304200000001, "min": 0.0002593304200000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036306258800000014, "min": 0.0036306258800000014, "max": 0.11284015702999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.038896266371011734, "min": 0.034444015473127365, "max": 0.45179611444473267, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.5445477366447449, "min": 0.4822162389755249, "max": 3.1625728607177734, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 396.7631578947368, "min": 319.4193548387097, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30154.0, "min": 15984.0, "max": 32395.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.550589454997527, "min": -1.0000000521540642, "max": 1.6686249803751707, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.84479857981205, "min": -32.000001668930054, "max": 156.21679832041264, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.550589454997527, "min": -1.0000000521540642, "max": 1.6686249803751707, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.84479857981205, "min": -32.000001668930054, "max": 156.21679832041264, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.15469382230864875, "min": 0.1177037685799102, "max": 10.439449346624315, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 11.756730495457305, "min": 10.367238094899221, "max": 167.03118954598904, "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": "1701259091", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701261443" }, "total": 2352.368342261, "count": 1, "self": 1.1859652390003248, "children": { "run_training.setup": { "total": 0.05293325799993909, "count": 1, "self": 0.05293325799993909 }, "TrainerController.start_learning": { "total": 2351.129443764, "count": 1, "self": 1.504482907081183, "children": { "TrainerController._reset_env": { "total": 3.1806877349999922, "count": 1, "self": 3.1806877349999922 }, "TrainerController.advance": { "total": 2346.323279792919, "count": 64056, "self": 1.5291312589297377, "children": { "env_step": { "total": 1706.7530147400346, "count": 64056, "self": 1569.974753281075, "children": { "SubprocessEnvManager._take_step": { "total": 135.87937432902413, "count": 64056, "self": 5.008008201937628, "children": { "TorchPolicy.evaluate": { "total": 130.8713661270865, "count": 62564, "self": 130.8713661270865 } } }, "workers": { "total": 0.8988871299354741, "count": 64056, "self": 0.0, "children": { "worker_root": { "total": 2346.172927239076, "count": 64056, "is_parallel": true, "self": 901.8222025890143, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020371989999148354, "count": 1, "is_parallel": true, "self": 0.0007274669999333128, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013097319999815227, "count": 8, "is_parallel": true, "self": 0.0013097319999815227 } } }, "UnityEnvironment.step": { "total": 0.07387179499983176, "count": 1, "is_parallel": true, "self": 0.0005989789997329353, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005042160000812146, "count": 1, "is_parallel": true, "self": 0.0005042160000812146 }, "communicator.exchange": { "total": 0.07091429299998708, "count": 1, "is_parallel": true, "self": 0.07091429299998708 }, "steps_from_proto": { "total": 0.0018543070000305306, "count": 1, "is_parallel": true, "self": 0.0004092650001439324, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014450419998865982, "count": 8, "is_parallel": true, "self": 0.0014450419998865982 } } } } } } }, "UnityEnvironment.step": { "total": 1444.350724650062, "count": 64055, "is_parallel": true, "self": 35.119208078121574, "children": { "UnityEnvironment._generate_step_input": { "total": 25.568672430008064, "count": 64055, "is_parallel": true, "self": 25.568672430008064 }, "communicator.exchange": { "total": 1280.8186922439982, "count": 64055, "is_parallel": true, "self": 1280.8186922439982 }, "steps_from_proto": { "total": 102.84415189793413, "count": 64055, "is_parallel": true, "self": 20.865667623893614, "children": { "_process_rank_one_or_two_observation": { "total": 81.97848427404051, "count": 512440, "is_parallel": true, "self": 81.97848427404051 } } } } } } } } } } }, "trainer_advance": { "total": 638.0411337939547, "count": 64056, "self": 2.798031949895403, "children": { "process_trajectory": { "total": 132.65540207806544, "count": 64056, "self": 132.39660974206527, "children": { "RLTrainer._checkpoint": { "total": 0.2587923360001696, "count": 2, "self": 0.2587923360001696 } } }, "_update_policy": { "total": 502.5876997659939, "count": 448, "self": 299.94785707199117, "children": { "TorchPPOOptimizer.update": { "total": 202.6398426940027, "count": 22824, "self": 202.6398426940027 } } } } } } }, "trainer_threads": { "total": 1.517999862699071e-06, "count": 1, "self": 1.517999862699071e-06 }, "TrainerController._save_models": { "total": 0.1209918109998398, "count": 1, "self": 0.0016357819999939238, "children": { "RLTrainer._checkpoint": { "total": 0.11935602899984588, "count": 1, "self": 0.11935602899984588 } } } } } } }