{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2583315670490265, "min": 0.21724596619606018, "max": 1.4476444721221924, "count": 54 }, "Pyramids.Policy.Entropy.sum": { "value": 7787.146484375, "min": 6513.90283203125, "max": 43915.7421875, "count": 54 }, "Pyramids.Step.mean": { "value": 1619931.0, "min": 29971.0, "max": 1619931.0, "count": 54 }, "Pyramids.Step.sum": { "value": 1619931.0, "min": 29971.0, "max": 1619931.0, "count": 54 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7295573949813843, "min": -0.0806223452091217, "max": 0.7685034871101379, "count": 54 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 211.57164001464844, "min": -19.268739700317383, "max": 224.777587890625, "count": 54 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0080729890614748, "min": -0.0080729890614748, "max": 0.35350826382637024, "count": 54 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.3411667346954346, "min": -2.3411667346954346, "max": 84.84197998046875, "count": 54 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07137363389434738, "min": 0.06481730613935117, "max": 0.07400298154106948, "count": 54 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9992308745208633, "min": 0.5494496235099618, "max": 1.0635391915663301, "count": 54 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016405179642215214, "min": 0.0005872933246925236, "max": 0.01656315394987663, "count": 54 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22967251499101302, "min": 0.007634813221002808, "max": 0.24844730924814942, "count": 54 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001394913035029167, "min": 0.0001394913035029167, "max": 0.00029828408807197084, "count": 54 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0019528782490408337, "min": 0.0019528782490408337, "max": 0.003969298376900566, "count": 54 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14649708333333336, "min": 0.14649708333333336, "max": 0.1994280291666667, "count": 54 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.050959166666667, "min": 1.5954242333333335, "max": 2.7674801333333336, "count": 54 }, "Pyramids.Policy.Beta.mean": { "value": 0.004655058625, "min": 0.004655058625, "max": 0.00994286011375, "count": 54 }, "Pyramids.Policy.Beta.sum": { "value": 0.06517082075, "min": 0.06517082075, "max": 0.13231763339000002, "count": 54 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009542092680931091, "min": 0.009392058476805687, "max": 0.44797787070274353, "count": 54 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13358929753303528, "min": 0.13148881494998932, "max": 3.5838229656219482, "count": 54 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 246.64406779661016, "min": 246.64406779661016, "max": 999.0, "count": 54 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29104.0, "min": 16386.0, "max": 32627.0, "count": 54 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.720013428510738, "min": -0.9999750521965325, "max": 1.74028300522071, "count": 54 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 204.68159799277782, "min": -31.99920167028904, "max": 206.18079817295074, "count": 54 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.720013428510738, "min": -0.9999750521965325, "max": 1.74028300522071, "count": 54 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 204.68159799277782, "min": -31.99920167028904, "max": 206.18079817295074, "count": 54 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02405466943478017, "min": 0.02405466943478017, "max": 8.963894915054826, "count": 54 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8625056627388403, "min": 2.7509678110363893, "max": 152.38621355593204, "count": 54 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 54 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707224872", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707229061" }, "total": 4188.915410618, "count": 1, "self": 0.38642960200013476, "children": { "run_training.setup": { "total": 0.05230056000004879, "count": 1, "self": 0.05230056000004879 }, "TrainerController.start_learning": { "total": 4188.476680456, "count": 1, "self": 3.050391059863614, "children": { "TrainerController._reset_env": { "total": 2.4704366639998625, "count": 1, "self": 2.4704366639998625 }, "TrainerController.advance": { "total": 4182.815778159137, "count": 104963, "self": 3.3258992652181405, "children": { "env_step": { "total": 3095.8190125259234, "count": 104963, "self": 2833.5798398598845, "children": { "SubprocessEnvManager._take_step": { "total": 260.2718381469265, "count": 104963, "self": 9.338487544950112, "children": { "TorchPolicy.evaluate": { "total": 250.93335060197637, "count": 101703, "self": 250.93335060197637 } } }, "workers": { "total": 1.967334519112228, "count": 104962, "self": 0.0, "children": { "worker_root": { "total": 4178.421330616076, "count": 104962, "is_parallel": true, "self": 1576.2555932979972, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019868429999405635, "count": 1, "is_parallel": true, "self": 0.0006634890003169858, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013233539996235777, "count": 8, "is_parallel": true, "self": 0.0013233539996235777 } } }, "UnityEnvironment.step": { "total": 0.05427606300008847, "count": 1, "is_parallel": true, "self": 0.0006261709997943399, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000490842000090197, "count": 1, "is_parallel": true, "self": 0.000490842000090197 }, "communicator.exchange": { "total": 0.051489238000158366, "count": 1, "is_parallel": true, "self": 0.051489238000158366 }, "steps_from_proto": { "total": 0.0016698120000455674, "count": 1, "is_parallel": true, "self": 0.00035045399999944493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013193580000461225, "count": 8, "is_parallel": true, "self": 0.0013193580000461225 } } } } } } }, "UnityEnvironment.step": { "total": 2602.165737318079, "count": 104961, "is_parallel": true, "self": 65.08685064810425, "children": { "UnityEnvironment._generate_step_input": { "total": 43.420788156953904, "count": 104961, "is_parallel": true, "self": 43.420788156953904 }, "communicator.exchange": { "total": 2315.9833638811124, "count": 104961, "is_parallel": true, "self": 2315.9833638811124 }, "steps_from_proto": { "total": 177.67473463190913, "count": 104961, "is_parallel": true, "self": 37.319316944888214, "children": { "_process_rank_one_or_two_observation": { "total": 140.35541768702092, "count": 839688, "is_parallel": true, "self": 140.35541768702092 } } } } } } } } } } }, "trainer_advance": { "total": 1083.6708663679951, "count": 104962, "self": 6.024583469179106, "children": { "process_trajectory": { "total": 221.3339910068123, "count": 104962, "self": 221.04260457281202, "children": { "RLTrainer._checkpoint": { "total": 0.2913864340002874, "count": 3, "self": 0.2913864340002874 } } }, "_update_policy": { "total": 856.3122918920037, "count": 750, "self": 498.8926279559762, "children": { "TorchPPOOptimizer.update": { "total": 357.4196639360275, "count": 37050, "self": 357.4196639360275 } } } } } } }, "trainer_threads": { "total": 1.5849991541472264e-06, "count": 1, "self": 1.5849991541472264e-06 }, "TrainerController._save_models": { "total": 0.14007298800061108, "count": 1, "self": 0.0022928650014364393, "children": { "RLTrainer._checkpoint": { "total": 0.13778012299917464, "count": 1, "self": 0.13778012299917464 } } } } } } }