{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2601408362388611, "min": 0.2559155523777008, "max": 1.458784818649292, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7758.43994140625, "min": 7698.0341796875, "max": 44253.6953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5825235247612, "min": -0.07833314687013626, "max": 0.6284767985343933, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.85415649414062, "min": -19.034954071044922, "max": 179.74436950683594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023653626441955566, "min": 0.0017012605676427484, "max": 0.5250244736671448, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.693976402282715, "min": 0.44062650203704834, "max": 124.43079376220703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06607691130812993, "min": 0.06562366439071152, "max": 0.07334363285640609, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.925076758313819, "min": 0.4865194067212448, "max": 1.0645389790297486, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015528213632627618, "min": 0.0011031727494809674, "max": 0.0165183034017294, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21739499085678665, "min": 0.011031727494809674, "max": 0.2365712957252981, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.62044031702857e-06, "min": 7.62044031702857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010668616443839998, "min": 0.00010668616443839998, "max": 0.003632742489085899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254011428571429, "min": 0.10254011428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355616, "min": 1.3886848, "max": 2.6109141, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026375741714285714, "min": 0.00026375741714285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369260384, "min": 0.00369260384, "max": 0.12111031859, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014202588237822056, "min": 0.014202588237822056, "max": 0.5674596428871155, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19883623719215393, "min": 0.19883623719215393, "max": 3.972217321395874, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.25, "min": 293.6847826086956, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29766.0, "min": 15984.0, "max": 33079.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5453723956798684, "min": -1.0000000521540642, "max": 1.684569543470507, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.44739842414856, "min": -30.534001648426056, "max": 164.99739910662174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5453723956798684, "min": -1.0000000521540642, "max": 1.684569543470507, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.44739842414856, "min": -30.534001648426056, "max": 164.99739910662174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05047286952455694, "min": 0.05047286952455694, "max": 12.726610448211432, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.391139648636454, "min": 4.3891922061447985, "max": 203.6257671713829, "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": "1703503888", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703506145" }, "total": 2257.101066633, "count": 1, "self": 0.526493467999444, "children": { "run_training.setup": { "total": 0.0470323780000399, "count": 1, "self": 0.0470323780000399 }, "TrainerController.start_learning": { "total": 2256.5275407870004, "count": 1, "self": 1.6238158281012147, "children": { "TrainerController._reset_env": { "total": 2.8922790850001547, "count": 1, "self": 2.8922790850001547 }, "TrainerController.advance": { "total": 2251.9253250028987, "count": 64031, "self": 1.6530552337399058, "children": { "env_step": { "total": 1607.9405614380776, "count": 64031, "self": 1467.8344618080046, "children": { "SubprocessEnvManager._take_step": { "total": 139.0881503340538, "count": 64031, "self": 4.958163277009135, "children": { "TorchPolicy.evaluate": { "total": 134.12998705704467, "count": 62557, "self": 134.12998705704467 } } }, "workers": { "total": 1.0179492960191965, "count": 64031, "self": 0.0, "children": { "worker_root": { "total": 2250.8953017520817, "count": 64031, "is_parallel": true, "self": 911.2605224831882, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002286181999807013, "count": 1, "is_parallel": true, "self": 0.0006356709995998244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016505110002071888, "count": 8, "is_parallel": true, "self": 0.0016505110002071888 } } }, "UnityEnvironment.step": { "total": 0.08132239499991556, "count": 1, "is_parallel": true, "self": 0.000685670000166283, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004462399997464672, "count": 1, "is_parallel": true, "self": 0.0004462399997464672 }, "communicator.exchange": { "total": 0.07861351799965632, "count": 1, "is_parallel": true, "self": 0.07861351799965632 }, "steps_from_proto": { "total": 0.0015769670003464853, "count": 1, "is_parallel": true, "self": 0.00031115499905354227, "children": { "_process_rank_one_or_two_observation": { "total": 0.001265812001292943, "count": 8, "is_parallel": true, "self": 0.001265812001292943 } } } } } } }, "UnityEnvironment.step": { "total": 1339.6347792688935, "count": 64030, "is_parallel": true, "self": 36.422397607803305, "children": { "UnityEnvironment._generate_step_input": { "total": 24.46495193102146, "count": 64030, "is_parallel": true, "self": 24.46495193102146 }, "communicator.exchange": { "total": 1178.016656538986, "count": 64030, "is_parallel": true, "self": 1178.016656538986 }, "steps_from_proto": { "total": 100.73077319108279, "count": 64030, "is_parallel": true, "self": 20.854891171345116, "children": { "_process_rank_one_or_two_observation": { "total": 79.87588201973767, "count": 512240, "is_parallel": true, "self": 79.87588201973767 } } } } } } } } } } }, "trainer_advance": { "total": 642.3317083310812, "count": 64031, "self": 3.1795282999901247, "children": { "process_trajectory": { "total": 128.96836103909527, "count": 64031, "self": 128.78803030709514, "children": { "RLTrainer._checkpoint": { "total": 0.1803307320001295, "count": 2, "self": 0.1803307320001295 } } }, "_update_policy": { "total": 510.18381899199585, "count": 451, "self": 302.732182299128, "children": { "TorchPPOOptimizer.update": { "total": 207.45163669286785, "count": 22797, "self": 207.45163669286785 } } } } } } }, "trainer_threads": { "total": 1.0660005500540137e-06, "count": 1, "self": 1.0660005500540137e-06 }, "TrainerController._save_models": { "total": 0.0861198049997256, "count": 1, "self": 0.0014431729996431386, "children": { "RLTrainer._checkpoint": { "total": 0.08467663200008246, "count": 1, "self": 0.08467663200008246 } } } } } } }