{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3666500449180603, "min": 0.365275114774704, "max": 1.4103314876556396, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11140.294921875, "min": 10812.1435546875, "max": 42783.81640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5927366018295288, "min": -0.09950734674930573, "max": 0.7072423100471497, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 166.55899047851562, "min": -23.98126983642578, "max": 203.685791015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007375817280262709, "min": -0.15236683189868927, "max": 0.36191678047180176, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.0726046562194824, "min": -42.20561218261719, "max": 85.77427673339844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06848967331335247, "min": 0.06385736586526036, "max": 0.07223557148351144, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9588554263869346, "min": 0.49361261027703196, "max": 1.0455625720399744, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016851221644306552, "min": 0.0008628091922366876, "max": 0.016851221644306552, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23591710302029173, "min": 0.006039664345656813, "max": 0.24718905597304305, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.599590323978567e-06, "min": 7.599590323978567e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010639426453569993, "min": 0.00010639426453569993, "max": 0.0033785570738144, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253316428571428, "min": 0.10253316428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354643, "min": 1.3691136000000002, "max": 2.5261856000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002630631121428571, "min": 0.0002630631121428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003682883569999999, "min": 0.003682883569999999, "max": 0.11264594144, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009887446649372578, "min": 0.009700154885649681, "max": 0.5670167803764343, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13842424750328064, "min": 0.13580216467380524, "max": 3.9691174030303955, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 302.4059405940594, "min": 264.7787610619469, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30543.0, "min": 15984.0, "max": 33477.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6381702853901552, "min": -1.0000000521540642, "max": 1.735221225076017, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.45519882440567, "min": -32.000001668930054, "max": 196.07999843358994, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6381702853901552, "min": -1.0000000521540642, "max": 1.735221225076017, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.45519882440567, "min": -32.000001668930054, "max": 196.07999843358994, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03118187372672422, "min": 0.027140908946558233, "max": 12.443020125851035, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1493692463991465, "min": 2.8974459202800062, "max": 199.08832201361656, "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": "1682275494", "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": "1682277846" }, "total": 2351.741900282, "count": 1, "self": 0.4407295290006914, "children": { "run_training.setup": { "total": 0.11050554300004478, "count": 1, "self": 0.11050554300004478 }, "TrainerController.start_learning": { "total": 2351.1906652099997, "count": 1, "self": 1.4478382790252908, "children": { "TrainerController._reset_env": { "total": 4.475606990000188, "count": 1, "self": 4.475606990000188 }, "TrainerController.advance": { "total": 2345.168154553974, "count": 64210, "self": 1.5859775070994147, "children": { "env_step": { "total": 1714.9181611279012, "count": 64210, "self": 1600.5561538948468, "children": { "SubprocessEnvManager._take_step": { "total": 113.43676104301767, "count": 64210, "self": 5.128247995074844, "children": { "TorchPolicy.evaluate": { "total": 108.30851304794282, "count": 62566, "self": 108.30851304794282 } } }, "workers": { "total": 0.9252461900366598, "count": 64210, "self": 0.0, "children": { "worker_root": { "total": 2345.7025924619657, "count": 64210, "is_parallel": true, "self": 867.1610060259945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020848320000368403, "count": 1, "is_parallel": true, "self": 0.0007272169996213051, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013576150004155352, "count": 8, "is_parallel": true, "self": 0.0013576150004155352 } } }, "UnityEnvironment.step": { "total": 0.10299721900014447, "count": 1, "is_parallel": true, "self": 0.00571646100001999, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000479107000046497, "count": 1, "is_parallel": true, "self": 0.000479107000046497 }, "communicator.exchange": { "total": 0.09163864500010277, "count": 1, "is_parallel": true, "self": 0.09163864500010277 }, "steps_from_proto": { "total": 0.005163005999975212, "count": 1, "is_parallel": true, "self": 0.003592226999671766, "children": { "_process_rank_one_or_two_observation": { "total": 0.001570779000303446, "count": 8, "is_parallel": true, "self": 0.001570779000303446 } } } } } } }, "UnityEnvironment.step": { "total": 1478.541586435971, "count": 64209, "is_parallel": true, "self": 33.95437562697339, "children": { "UnityEnvironment._generate_step_input": { "total": 25.890193911974166, "count": 64209, "is_parallel": true, "self": 25.890193911974166 }, "communicator.exchange": { "total": 1314.9918897530245, "count": 64209, "is_parallel": true, "self": 1314.9918897530245 }, "steps_from_proto": { "total": 103.7051271439991, "count": 64209, "is_parallel": true, "self": 22.416614795071382, "children": { "_process_rank_one_or_two_observation": { "total": 81.28851234892772, "count": 513672, "is_parallel": true, "self": 81.28851234892772 } } } } } } } } } } }, "trainer_advance": { "total": 628.6640159189737, "count": 64210, "self": 2.749028301927865, "children": { "process_trajectory": { "total": 114.37113254304609, "count": 64210, "self": 114.15667400604593, "children": { "RLTrainer._checkpoint": { "total": 0.21445853700015505, "count": 2, "self": 0.21445853700015505 } } }, "_update_policy": { "total": 511.5438550739998, "count": 452, "self": 326.9257647660304, "children": { "TorchPPOOptimizer.update": { "total": 184.6180903079694, "count": 22833, "self": 184.6180903079694 } } } } } } }, "trainer_threads": { "total": 1.0429998837935273e-06, "count": 1, "self": 1.0429998837935273e-06 }, "TrainerController._save_models": { "total": 0.09906434399999853, "count": 1, "self": 0.001476240000101825, "children": { "RLTrainer._checkpoint": { "total": 0.0975881039998967, "count": 1, "self": 0.0975881039998967 } } } } } } }