{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13623328506946564, "min": 0.12003583461046219, "max": 1.4792479276657104, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4093.53759765625, "min": 3608.75732421875, "max": 44874.46484375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999893.0, "min": 29959.0, "max": 2999893.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999893.0, "min": 29959.0, "max": 2999893.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8191083669662476, "min": -0.09184083342552185, "max": 0.8728657364845276, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 240.81785583496094, "min": -22.13364028930664, "max": 267.096923828125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009215716272592545, "min": -0.036827292293310165, "max": 0.389845609664917, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.709420680999756, "min": -9.53826904296875, "max": 92.78325653076172, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06831702833560052, "min": 0.0638048921401302, "max": 0.07469888852765075, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9564383966984072, "min": 0.5626987687204672, "max": 1.0831885099726017, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014527680530417933, "min": 0.0011067030370523266, "max": 0.01620561550382762, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20338752742585106, "min": 0.012173733407575592, "max": 0.23779433694617896, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4599709419476185e-06, "min": 1.4599709419476185e-06, "max": 0.00029828248807250415, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.043959318726666e-05, "min": 2.043959318726666e-05, "max": 0.0040272403575866, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048662380952382, "min": 0.10048662380952382, "max": 0.19942749583333336, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068127333333336, "min": 1.4068127333333336, "max": 2.8424134000000008, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.861371857142855e-05, "min": 5.861371857142855e-05, "max": 0.00994280683375, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008205920599999997, "min": 0.0008205920599999997, "max": 0.13425709866000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0072586615569889545, "min": 0.007066840305924416, "max": 0.37320676445961, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10162126272916794, "min": 0.09977103024721146, "max": 2.98565411567688, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 219.8320610687023, "min": 202.13194444444446, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28798.0, "min": 17013.0, "max": 32833.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.764899225635383, "min": -0.9999375520274043, "max": 1.7978680457712874, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 231.20179855823517, "min": -31.998001664876938, "max": 258.8929985910654, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.764899225635383, "min": -0.9999375520274043, "max": 1.7978680457712874, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 231.20179855823517, "min": -31.998001664876938, "max": 258.8929985910654, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016296768891478478, "min": 0.015196574029554691, "max": 7.055088243550724, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1348767247836804, "min": 2.1040862517547794, "max": 126.99158838391304, "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": "1759834711", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1759842430" }, "total": 7718.5586124169995, "count": 1, "self": 0.82861161099936, "children": { "run_training.setup": { "total": 0.02427679199990962, "count": 1, "self": 0.02427679199990962 }, "TrainerController.start_learning": { "total": 7717.705724014, "count": 1, "self": 4.415514026686651, "children": { "TrainerController._reset_env": { "total": 2.097863852000046, "count": 1, "self": 2.097863852000046 }, "TrainerController.advance": { "total": 7711.104759981315, "count": 195166, "self": 4.485831799011066, "children": { "env_step": { "total": 5619.2253351331765, "count": 195166, "self": 5146.192476863289, "children": { "SubprocessEnvManager._take_step": { "total": 470.4291130658389, "count": 195166, "self": 14.812160536921965, "children": { "TorchPolicy.evaluate": { "total": 455.61695252891695, "count": 187562, "self": 455.61695252891695 } } }, "workers": { "total": 2.6037452040482094, "count": 195166, "self": 0.0, "children": { "worker_root": { "total": 7696.8161066919165, "count": 195166, "is_parallel": true, "self": 2926.8241982308346, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018802889999278705, "count": 1, "is_parallel": true, "self": 0.0006799719999435183, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012003169999843522, "count": 8, "is_parallel": true, "self": 0.0012003169999843522 } } }, "UnityEnvironment.step": { "total": 0.05261544599989065, "count": 1, "is_parallel": true, "self": 0.0005694219998986227, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004918089998682262, "count": 1, "is_parallel": true, "self": 0.0004918089998682262 }, "communicator.exchange": { "total": 0.04986780000012914, "count": 1, "is_parallel": true, "self": 0.04986780000012914 }, "steps_from_proto": { "total": 0.0016864149999946676, "count": 1, "is_parallel": true, "self": 0.00033889899987116223, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013475160001235054, "count": 8, "is_parallel": true, "self": 0.0013475160001235054 } } } } } } }, "UnityEnvironment.step": { "total": 4769.991908461082, "count": 195165, "is_parallel": true, "self": 105.44984077729987, "children": { "UnityEnvironment._generate_step_input": { "total": 74.69839871826889, "count": 195165, "is_parallel": true, "self": 74.69839871826889 }, "communicator.exchange": { "total": 4239.445248036689, "count": 195165, "is_parallel": true, "self": 4239.445248036689 }, "steps_from_proto": { "total": 350.39842092882486, "count": 195165, "is_parallel": true, "self": 72.66200814163085, "children": { "_process_rank_one_or_two_observation": { "total": 277.736412787194, "count": 1561320, "is_parallel": true, "self": 277.736412787194 } } } } } } } } } } }, "trainer_advance": { "total": 2087.393593049127, "count": 195166, "self": 8.873767109379514, "children": { "process_trajectory": { "total": 413.53712991973384, "count": 195166, "self": 412.95893452973337, "children": { "RLTrainer._checkpoint": { "total": 0.5781953900004737, "count": 6, "self": 0.5781953900004737 } } }, "_update_policy": { "total": 1664.982696020014, "count": 1406, "self": 926.5310497609541, "children": { "TorchPPOOptimizer.update": { "total": 738.4516462590598, "count": 68385, "self": 738.4516462590598 } } } } } } }, "trainer_threads": { "total": 1.116999555961229e-06, "count": 1, "self": 1.116999555961229e-06 }, "TrainerController._save_models": { "total": 0.08758503699937137, "count": 1, "self": 0.0013330899982975097, "children": { "RLTrainer._checkpoint": { "total": 0.08625194700107386, "count": 1, "self": 0.08625194700107386 } } } } } } }