ahaque12's picture
First Push
8763fd1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6743969917297363,
"min": 0.5893281102180481,
"max": 1.5100557804107666,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 20415.345703125,
"min": 17783.564453125,
"max": 45809.05078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989960.0,
"min": 29952.0,
"max": 989960.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989960.0,
"min": 29952.0,
"max": 989960.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.21724340319633484,
"min": -0.10147688537836075,
"max": 0.2724071741104126,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 54.745338439941406,
"min": -24.455928802490234,
"max": 69.46382904052734,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -4.66960334777832,
"min": -4.66960334777832,
"max": 0.5553449988365173,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -1176.739990234375,
"min": -1176.739990234375,
"max": 143.8343505859375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06566382596140934,
"min": 0.06536241007270292,
"max": 0.07335298180311371,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9192935634597307,
"min": 0.513470872621796,
"max": 1.0358804978690492,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 2.293325950261153,
"min": 4.569567698299375e-05,
"max": 2.94032170976113,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 32.106563303656145,
"min": 0.0006397394777619125,
"max": 41.16450393665582,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.662783160057147e-06,
"min": 7.662783160057147e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010727896424080005,
"min": 0.00010727896424080005,
"max": 0.0035074310308564,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025542285714286,
"min": 0.1025542285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4357592000000003,
"min": 1.3886848,
"max": 2.5691436,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002651674342857144,
"min": 0.0002651674342857144,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037123440800000016,
"min": 0.0037123440800000016,
"max": 0.11693744564000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010499651543796062,
"min": 0.010499651543796062,
"max": 0.3303826153278351,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14699512720108032,
"min": 0.14699512720108032,
"max": 2.312678337097168,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 675.6363636363636,
"min": 603.4117647058823,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29728.0,
"min": 15984.0,
"max": 33668.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.6423408761620522,
"min": -1.0000000521540642,
"max": 1.111099968701601,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 28.262998551130295,
"min": -31.993201658129692,
"max": 55.55499843508005,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.6423408761620522,
"min": -1.0000000521540642,
"max": 1.111099968701601,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 28.262998551130295,
"min": -31.993201658129692,
"max": 55.55499843508005,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0737597448420605,
"min": 0.07060547071447824,
"max": 6.784127460792661,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.245428773050662,
"min": 3.245428773050662,
"max": 108.54603937268257,
"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": "1702429279",
"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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702431548"
},
"total": 2269.190598701,
"count": 1,
"self": 0.49012114399965867,
"children": {
"run_training.setup": {
"total": 0.09325224300005175,
"count": 1,
"self": 0.09325224300005175
},
"TrainerController.start_learning": {
"total": 2268.607225314,
"count": 1,
"self": 1.7274490469585544,
"children": {
"TrainerController._reset_env": {
"total": 4.1847432819999995,
"count": 1,
"self": 4.1847432819999995
},
"TrainerController.advance": {
"total": 2262.6072622860415,
"count": 63420,
"self": 1.6826672300921928,
"children": {
"env_step": {
"total": 1599.9584103899458,
"count": 63420,
"self": 1454.0424382949682,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.87674237498936,
"count": 63420,
"self": 5.151986811001279,
"children": {
"TorchPolicy.evaluate": {
"total": 139.72475556398808,
"count": 62578,
"self": 139.72475556398808
}
}
},
"workers": {
"total": 1.0392297199882705,
"count": 63420,
"self": 0.0,
"children": {
"worker_root": {
"total": 2263.7137994450122,
"count": 63420,
"is_parallel": true,
"self": 938.4939834730308,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025694060000205354,
"count": 1,
"is_parallel": true,
"self": 0.0007622460002494336,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018071599997711019,
"count": 8,
"is_parallel": true,
"self": 0.0018071599997711019
}
}
},
"UnityEnvironment.step": {
"total": 0.04733838800007106,
"count": 1,
"is_parallel": true,
"self": 0.000575155999740673,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047802200015212293,
"count": 1,
"is_parallel": true,
"self": 0.00047802200015212293
},
"communicator.exchange": {
"total": 0.04461835400002201,
"count": 1,
"is_parallel": true,
"self": 0.04461835400002201
},
"steps_from_proto": {
"total": 0.0016668560001562582,
"count": 1,
"is_parallel": true,
"self": 0.00038294499972835183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012839110004279064,
"count": 8,
"is_parallel": true,
"self": 0.0012839110004279064
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1325.2198159719815,
"count": 63419,
"is_parallel": true,
"self": 35.92780748295081,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.725119259987196,
"count": 63419,
"is_parallel": true,
"self": 24.725119259987196
},
"communicator.exchange": {
"total": 1161.7169718150033,
"count": 63419,
"is_parallel": true,
"self": 1161.7169718150033
},
"steps_from_proto": {
"total": 102.84991741404019,
"count": 63419,
"is_parallel": true,
"self": 21.38370171611382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.46621569792637,
"count": 507352,
"is_parallel": true,
"self": 81.46621569792637
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 660.9661846660035,
"count": 63420,
"self": 3.1416680350057504,
"children": {
"process_trajectory": {
"total": 132.87818339999944,
"count": 63420,
"self": 132.65748098299923,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22070241700021143,
"count": 2,
"self": 0.22070241700021143
}
}
},
"_update_policy": {
"total": 524.9463332309983,
"count": 447,
"self": 314.59059709502753,
"children": {
"TorchPPOOptimizer.update": {
"total": 210.3557361359708,
"count": 22788,
"self": 210.3557361359708
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.739998520468362e-07,
"count": 1,
"self": 8.739998520468362e-07
},
"TrainerController._save_models": {
"total": 0.08776982500012309,
"count": 1,
"self": 0.001314344000093115,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08645548100002998,
"count": 1,
"self": 0.08645548100002998
}
}
}
}
}
}
}