{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15871793031692505, "min": 0.15560756623744965, "max": 1.4435852766036987, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4797.0908203125, "min": 4623.61865234375, "max": 43792.6015625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999985.0, "min": 29952.0, "max": 2999985.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999985.0, "min": 29952.0, "max": 2999985.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8098489046096802, "min": -0.14433130621910095, "max": 0.8098489046096802, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 245.38421630859375, "min": -34.206520080566406, "max": 245.38421630859375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0018742886604741216, "min": -0.02372102066874504, "max": 0.30055710673332214, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5679094791412354, "min": -6.831654071807861, "max": 72.43426513671875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06566559385467971, "min": 0.061930916860029835, "max": 0.0736932415734156, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9849839078201957, "min": 0.5135945621165366, "max": 1.0875620015008904, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014842968481003908, "min": 0.0002883074703097436, "max": 0.015729696505069213, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22264452721505862, "min": 0.003171382173407179, "max": 0.23594544757603822, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4785395071866674e-06, "min": 1.4785395071866674e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.217809260780001e-05, "min": 2.217809260780001e-05, "max": 0.003969195876934733, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049281333333333, "min": 0.10049281333333333, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5073922, "min": 1.3962282666666668, "max": 2.7524788000000004, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.923205200000003e-05, "min": 5.923205200000003e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008884807800000004, "min": 0.0008884807800000004, "max": 0.13231422014000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004117712844163179, "min": 0.003823485691100359, "max": 0.4440358281135559, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06176568940281868, "min": 0.0535288006067276, "max": 3.108250856399536, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 243.04032258064515, "min": 228.63970588235293, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30137.0, "min": 15984.0, "max": 33402.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7408290219403082, "min": -1.0000000521540642, "max": 1.7566499852520578, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 215.86279872059822, "min": -32.000001668930054, "max": 238.90439799427986, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7408290219403082, "min": -1.0000000521540642, "max": 1.7566499852520578, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 215.86279872059822, "min": -32.000001668930054, "max": 238.90439799427986, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.010619096162343104, "min": 0.009678223745889709, "max": 8.590630190446973, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.316767924130545, "min": 1.150322192137537, "max": 137.45008304715157, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690454994", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690462657" }, "total": 7663.162056414, "count": 1, "self": 0.4762042789998304, "children": { "run_training.setup": { "total": 0.051309037000009994, "count": 1, "self": 0.051309037000009994 }, "TrainerController.start_learning": { "total": 7662.634543098, "count": 1, "self": 5.59728980793443, "children": { "TrainerController._reset_env": { "total": 4.262320954999723, "count": 1, "self": 4.262320954999723 }, "TrainerController.advance": { "total": 7652.675169394064, "count": 193756, "self": 5.036954099152354, "children": { "env_step": { "total": 5597.779426146026, "count": 193756, "self": 5214.980735213934, "children": { "SubprocessEnvManager._take_step": { "total": 379.555495414053, "count": 193756, "self": 15.766468577334763, "children": { "TorchPolicy.evaluate": { "total": 363.7890268367182, "count": 187572, "self": 363.7890268367182 } } }, "workers": { "total": 3.2431955180386467, "count": 193756, "self": 0.0, "children": { "worker_root": { "total": 7644.04787859788, "count": 193756, "is_parallel": true, "self": 2821.3691108118155, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001837188000081369, "count": 1, "is_parallel": true, "self": 0.0005870619997949689, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012501260002864, "count": 8, "is_parallel": true, "self": 0.0012501260002864 } } }, "UnityEnvironment.step": { "total": 0.05397998299986284, "count": 1, "is_parallel": true, "self": 0.0006088449999879231, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005268519998935517, "count": 1, "is_parallel": true, "self": 0.0005268519998935517 }, "communicator.exchange": { "total": 0.05084539400013455, "count": 1, "is_parallel": true, "self": 0.05084539400013455 }, "steps_from_proto": { "total": 0.001998891999846819, "count": 1, "is_parallel": true, "self": 0.0003840180006591254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016148739991876937, "count": 8, "is_parallel": true, "self": 0.0016148739991876937 } } } } } } }, "UnityEnvironment.step": { "total": 4822.678767786065, "count": 193755, "is_parallel": true, "self": 112.84729675838571, "children": { "UnityEnvironment._generate_step_input": { "total": 73.08691379726133, "count": 193755, "is_parallel": true, "self": 73.08691379726133 }, "communicator.exchange": { "total": 4301.442670149378, "count": 193755, "is_parallel": true, "self": 4301.442670149378 }, "steps_from_proto": { "total": 335.30188708104015, "count": 193755, "is_parallel": true, "self": 70.01415561331669, "children": { "_process_rank_one_or_two_observation": { "total": 265.28773146772346, "count": 1550040, "is_parallel": true, "self": 265.28773146772346 } } } } } } } } } } }, "trainer_advance": { "total": 2049.858789148886, "count": 193756, "self": 10.051488206072008, "children": { "process_trajectory": { "total": 352.6715858258108, "count": 193756, "self": 351.9902700328121, "children": { "RLTrainer._checkpoint": { "total": 0.6813157929987028, "count": 6, "self": 0.6813157929987028 } } }, "_update_policy": { "total": 1687.1357151170032, "count": 1396, "self": 1097.1759553950992, "children": { "TorchPPOOptimizer.update": { "total": 589.959759721904, "count": 68337, "self": 589.959759721904 } } } } } } }, "trainer_threads": { "total": 1.047999830916524e-06, "count": 1, "self": 1.047999830916524e-06 }, "TrainerController._save_models": { "total": 0.09976189300141414, "count": 1, "self": 0.0016603930016572122, "children": { "RLTrainer._checkpoint": { "total": 0.09810149999975692, "count": 1, "self": 0.09810149999975692 } } } } } } }