ppo-Pyramids / run_logs /timers.json
Tyraex's picture
First Push
6d4a0eb verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.15289455652236938,
"min": 0.15289455652236938,
"max": 0.22067362070083618,
"count": 34
},
"Pyramids.Policy.Entropy.sum": {
"value": 4621.0849609375,
"min": 2443.29833984375,
"max": 6157.3564453125,
"count": 34
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 269.60185185185185,
"min": 212.1627906976744,
"max": 269.60185185185185,
"count": 34
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29117.0,
"min": 9123.0,
"max": 31464.0,
"count": 34
},
"Pyramids.Step.mean": {
"value": 2999904.0,
"min": 2009912.0,
"max": 2999904.0,
"count": 34
},
"Pyramids.Step.sum": {
"value": 2999904.0,
"min": 2009912.0,
"max": 2999904.0,
"count": 34
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7522175908088684,
"min": 0.6867677569389343,
"max": 0.824851930141449,
"count": 34
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 216.638671875,
"min": 67.30323791503906,
"max": 252.0583953857422,
"count": 34
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0007098768837749958,
"min": -0.016200093552470207,
"max": 0.015306035056710243,
"count": 34
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.2044445425271988,
"min": -4.827628135681152,
"max": 4.469362258911133,
"count": 34
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7118759106982637,
"min": 1.648581342234955,
"max": 1.7878371979608092,
"count": 34
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 184.88259835541248,
"min": 76.8769995123148,
"max": 238.69199825823307,
"count": 34
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7118759106982637,
"min": 1.648581342234955,
"max": 1.7878371979608092,
"count": 34
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 184.88259835541248,
"min": 76.8769995123148,
"max": 238.69199825823307,
"count": 34
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.021116538723786275,
"min": 0.017790217164287143,
"max": 0.02492618942558509,
"count": 34
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.2805861821689177,
"min": 0.8723248280584812,
"max": 2.749446797693963,
"count": 34
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06645269455362318,
"min": 0.06497105862945318,
"max": 0.07290959148797102,
"count": 34
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9967904183043478,
"min": 0.2681261481096347,
"max": 1.0936438723195654,
"count": 34
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01478061941969726,
"min": 0.01346236491938018,
"max": 0.017154385229029383,
"count": 34
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22170929129545888,
"min": 0.06861754091611753,
"max": 0.2558162071994351,
"count": 34
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5255061581977754e-06,
"min": 1.5255061581977754e-06,
"max": 9.948556683816666e-05,
"count": 34
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.288259237296663e-05,
"min": 2.288259237296663e-05,
"max": 0.0014179531273493,
"count": 34
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10050846888888888,
"min": 0.10050846888888888,
"max": 0.13316183333333337,
"count": 34
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5076270333333333,
"min": 0.5326473333333335,
"max": 1.9726507000000002,
"count": 34
},
"Pyramids.Policy.Beta.mean": {
"value": 6.079604199999993e-05,
"min": 6.079604199999993e-05,
"max": 0.0033228671500000004,
"count": 34
},
"Pyramids.Policy.Beta.sum": {
"value": 0.000911940629999999,
"min": 0.000911940629999999,
"max": 0.04736780493000001,
"count": 34
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007543759420514107,
"min": 0.007363577373325825,
"max": 0.009161488153040409,
"count": 34
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11315639317035675,
"min": 0.036645952612161636,
"max": 0.132064089179039,
"count": 34
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 34
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 34
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1760702217",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
"command_line_arguments": "/local_scratch/ahmohame/MyRLProj/.venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1760704758"
},
"total": 2541.0156352190534,
"count": 1,
"self": 0.42585068312473595,
"children": {
"run_training.setup": {
"total": 0.01982548099476844,
"count": 1,
"self": 0.01982548099476844
},
"TrainerController.start_learning": {
"total": 2540.569959054934,
"count": 1,
"self": 1.1060997820459306,
"children": {
"TrainerController._reset_env": {
"total": 2.9760029109893367,
"count": 1,
"self": 2.9760029109893367
},
"TrainerController.advance": {
"total": 2536.4246685889084,
"count": 65782,
"self": 0.9965739522594959,
"children": {
"env_step": {
"total": 1770.4080325771356,
"count": 65782,
"self": 1657.2321162994485,
"children": {
"SubprocessEnvManager._take_step": {
"total": 112.51392729778308,
"count": 65782,
"self": 3.606503952294588,
"children": {
"TorchPolicy.evaluate": {
"total": 108.9074233454885,
"count": 62561,
"self": 108.9074233454885
}
}
},
"workers": {
"total": 0.6619889799039811,
"count": 65782,
"self": 0.0,
"children": {
"worker_root": {
"total": 2537.056739655207,
"count": 65782,
"is_parallel": true,
"self": 992.4253368276404,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003727403935045004,
"count": 1,
"is_parallel": true,
"self": 0.0010196649236604571,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027077390113845468,
"count": 8,
"is_parallel": true,
"self": 0.0027077390113845468
}
}
},
"UnityEnvironment.step": {
"total": 0.053242832073010504,
"count": 1,
"is_parallel": true,
"self": 0.0008654361590743065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007460089400410652,
"count": 1,
"is_parallel": true,
"self": 0.0007460089400410652
},
"communicator.exchange": {
"total": 0.049158178037032485,
"count": 1,
"is_parallel": true,
"self": 0.049158178037032485
},
"steps_from_proto": {
"total": 0.0024732089368626475,
"count": 1,
"is_parallel": true,
"self": 0.0005333300214260817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019398789154365659,
"count": 8,
"is_parallel": true,
"self": 0.0019398789154365659
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1544.6314028275665,
"count": 65781,
"is_parallel": true,
"self": 47.59692893491592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 34.48821103293449,
"count": 65781,
"is_parallel": true,
"self": 34.48821103293449
},
"communicator.exchange": {
"total": 1325.8077641566051,
"count": 65781,
"is_parallel": true,
"self": 1325.8077641566051
},
"steps_from_proto": {
"total": 136.73849870311096,
"count": 65781,
"is_parallel": true,
"self": 28.868332263664342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 107.87016643944662,
"count": 526248,
"is_parallel": true,
"self": 107.87016643944662
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 765.0200620595133,
"count": 65782,
"self": 2.3117871991125867,
"children": {
"process_trajectory": {
"total": 99.78814935754053,
"count": 65782,
"self": 99.56120990449563,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22693945304490626,
"count": 3,
"self": 0.22693945304490626
}
}
},
"_update_policy": {
"total": 662.9201255028602,
"count": 474,
"self": 302.62621632928494,
"children": {
"TorchPPOOptimizer.update": {
"total": 360.29390917357523,
"count": 22815,
"self": 360.29390917357523
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.980277925729752e-07,
"count": 1,
"self": 8.980277925729752e-07
},
"TrainerController._save_models": {
"total": 0.06318687496241182,
"count": 1,
"self": 0.0011085569858551025,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06207831797655672,
"count": 1,
"self": 0.06207831797655672
}
}
}
}
}
}
}