{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3695603311061859, "min": 0.3656662404537201, "max": 1.4379774332046509, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11228.720703125, "min": 11013.6708984375, "max": 43622.484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6549415588378906, "min": -0.07943497598171234, "max": 0.6753299236297607, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 187.96823120117188, "min": -19.143829345703125, "max": 194.49501037597656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009754575788974762, "min": 0.0017544170841574669, "max": 0.3510623574256897, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.79956316947937, "min": 0.4859735369682312, "max": 83.2017822265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0696561697266242, "min": 0.06568736907017107, "max": 0.07377090357369319, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9751863761727387, "min": 0.4917831659135034, "max": 1.0610465479257982, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016841941632308243, "min": 0.0014188096310544932, "max": 0.01710731952473344, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2357871828523154, "min": 0.009931667417381452, "max": 0.2501647881364596, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.574861760792856e-06, "min": 7.574861760792856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010604806465109998, "min": 0.00010604806465109998, "max": 0.0035080610306464, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252492142857143, "min": 0.10252492142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353489000000001, "min": 1.3691136000000002, "max": 2.5693536, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026223965071428567, "min": 0.00026223965071428567, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036713551099999994, "min": 0.0036713551099999994, "max": 0.11695842464, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011613845825195312, "min": 0.011613845825195312, "max": 0.5306715369224548, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16259384155273438, "min": 0.16259384155273438, "max": 3.714700698852539, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 282.22857142857146, "min": 280.04587155963304, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29634.0, "min": 15984.0, "max": 33027.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6796590277836436, "min": -1.0000000521540642, "max": 1.7040097882934646, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.36419791728258, "min": -32.000001668930054, "max": 181.47259814292192, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6796590277836436, "min": -1.0000000521540642, "max": 1.7040097882934646, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.36419791728258, "min": -32.000001668930054, "max": 181.47259814292192, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.034018340713685445, "min": 0.034018340713685445, "max": 10.693337187170982, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5719257749369717, "min": 3.571084239287302, "max": 171.09339499473572, "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": "1687908682", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687910927" }, "total": 2245.2982545349996, "count": 1, "self": 0.4756851539996205, "children": { "run_training.setup": { "total": 0.039400620000037634, "count": 1, "self": 0.039400620000037634 }, "TrainerController.start_learning": { "total": 2244.783168761, "count": 1, "self": 1.3491435260493745, "children": { "TrainerController._reset_env": { "total": 4.786498280000046, "count": 1, "self": 4.786498280000046 }, "TrainerController.advance": { "total": 2238.55264446595, "count": 64096, "self": 1.3849333799471424, "children": { "env_step": { "total": 1609.0986441410196, "count": 64096, "self": 1500.2147607408965, "children": { "SubprocessEnvManager._take_step": { "total": 108.08499467007869, "count": 64096, "self": 4.681671674092058, "children": { "TorchPolicy.evaluate": { "total": 103.40332299598663, "count": 62559, "self": 103.40332299598663 } } }, "workers": { "total": 0.7988887300444958, "count": 64096, "self": 0.0, "children": { "worker_root": { "total": 2239.5954521960925, "count": 64096, "is_parallel": true, "self": 850.7204507801139, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018939029999955892, "count": 1, "is_parallel": true, "self": 0.0005801280002515341, "children": { "_process_rank_one_or_two_observation": { "total": 0.001313774999744055, "count": 8, "is_parallel": true, "self": 0.001313774999744055 } } }, "UnityEnvironment.step": { "total": 0.07602796600008332, "count": 1, "is_parallel": true, "self": 0.0005676370001310715, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004747929999666667, "count": 1, "is_parallel": true, "self": 0.0004747929999666667 }, "communicator.exchange": { "total": 0.07311825299996144, "count": 1, "is_parallel": true, "self": 0.07311825299996144 }, "steps_from_proto": { "total": 0.0018672830000241447, "count": 1, "is_parallel": true, "self": 0.0003802480001695585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014870349998545862, "count": 8, "is_parallel": true, "self": 0.0014870349998545862 } } } } } } }, "UnityEnvironment.step": { "total": 1388.8750014159787, "count": 64095, "is_parallel": true, "self": 33.88781133391899, "children": { "UnityEnvironment._generate_step_input": { "total": 21.91642906100401, "count": 64095, "is_parallel": true, "self": 21.91642906100401 }, "communicator.exchange": { "total": 1233.365246109019, "count": 64095, "is_parallel": true, "self": 1233.365246109019 }, "steps_from_proto": { "total": 99.70551491203673, "count": 64095, "is_parallel": true, "self": 19.427608965021363, "children": { "_process_rank_one_or_two_observation": { "total": 80.27790594701537, "count": 512760, "is_parallel": true, "self": 80.27790594701537 } } } } } } } } } } }, "trainer_advance": { "total": 628.0690669449834, "count": 64096, "self": 2.556651933937701, "children": { "process_trajectory": { "total": 107.13645258504675, "count": 64096, "self": 106.9357295020468, "children": { "RLTrainer._checkpoint": { "total": 0.20072308299995711, "count": 2, "self": 0.20072308299995711 } } }, "_update_policy": { "total": 518.375962425999, "count": 451, "self": 331.6901736310201, "children": { "TorchPPOOptimizer.update": { "total": 186.68578879497886, "count": 22788, "self": 186.68578879497886 } } } } } } }, "trainer_threads": { "total": 1.0030003068095539e-06, "count": 1, "self": 1.0030003068095539e-06 }, "TrainerController._save_models": { "total": 0.094881486000304, "count": 1, "self": 0.0013733480000155396, "children": { "RLTrainer._checkpoint": { "total": 0.09350813800028845, "count": 1, "self": 0.09350813800028845 } } } } } } }