PPO-Pyramids1 / run_logs /timers.json
Spur1ous's picture
First Push
b50d444 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.48499083518981934,
"min": 0.4563876986503601,
"max": 1.4447362422943115,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14681.642578125,
"min": 13479.8671875,
"max": 43827.51953125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989970.0,
"min": 29973.0,
"max": 989970.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989970.0,
"min": 29973.0,
"max": 989970.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4434652328491211,
"min": -0.1011827141046524,
"max": 0.4434652328491211,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 119.73561096191406,
"min": -24.283851623535156,
"max": 119.73561096191406,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.002688574604690075,
"min": -0.00469829048961401,
"max": 0.23333647847175598,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.7259151339530945,
"min": -1.2168571949005127,
"max": 56.000755310058594,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06906455842480581,
"min": 0.06613664766967607,
"max": 0.07536361832859549,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0359683763720873,
"min": 0.6029089466287639,
"max": 1.0671237340429798,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011028579994712748,
"min": 0.0002440516378128421,
"max": 0.012676641630213112,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16542869992069123,
"min": 0.0034167229293797893,
"max": 0.18458323836966883,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.414557528513333e-06,
"min": 7.414557528513333e-06,
"max": 0.0002947647017451,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001112183629277,
"min": 0.0001112183629277,
"max": 0.003507350030883399,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247148666666667,
"min": 0.10247148666666667,
"max": 0.1982549,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5370723,
"min": 1.4775340000000001,
"max": 2.5691165999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000256901518,
"min": 0.000256901518,
"max": 0.009825664509999998,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038535227700000002,
"min": 0.0038535227700000002,
"max": 0.11693474834,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008505865931510925,
"min": 0.008505865931510925,
"max": 0.40028274059295654,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12758798897266388,
"min": 0.127574622631073,
"max": 3.2022619247436523,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 450.9852941176471,
"min": 436.0147058823529,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30667.0,
"min": 17539.0,
"max": 33572.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4292753447873006,
"min": -0.9997677932823857,
"max": 1.4292753447873006,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 98.61999879032373,
"min": -30.99280159175396,
"max": 98.61999879032373,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4292753447873006,
"min": -0.9997677932823857,
"max": 1.4292753447873006,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 98.61999879032373,
"min": -30.99280159175396,
"max": 98.61999879032373,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04053224946635411,
"min": 0.04053224946635411,
"max": 7.593862218989266,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.7967252131784335,
"min": 2.6926840419218934,
"max": 136.6895199418068,
"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": "1744008119",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744010335"
},
"total": 2216.48599235,
"count": 1,
"self": 0.7962067269991167,
"children": {
"run_training.setup": {
"total": 0.01957241300010537,
"count": 1,
"self": 0.01957241300010537
},
"TrainerController.start_learning": {
"total": 2215.6702132100004,
"count": 1,
"self": 1.3465812720628492,
"children": {
"TrainerController._reset_env": {
"total": 2.9539998319999086,
"count": 1,
"self": 2.9539998319999086
},
"TrainerController.advance": {
"total": 2211.284230717938,
"count": 63526,
"self": 1.372795230934571,
"children": {
"env_step": {
"total": 1532.7976692930235,
"count": 63526,
"self": 1378.726107839985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.31208955704915,
"count": 63526,
"self": 4.5986106570017,
"children": {
"TorchPolicy.evaluate": {
"total": 148.71347890004745,
"count": 62557,
"self": 148.71347890004745
}
}
},
"workers": {
"total": 0.7594718959894635,
"count": 63526,
"self": 0.0,
"children": {
"worker_root": {
"total": 2210.541000193952,
"count": 63526,
"is_parallel": true,
"self": 942.9029439069593,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024969309999960387,
"count": 1,
"is_parallel": true,
"self": 0.0007049369999094779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017919940000865608,
"count": 8,
"is_parallel": true,
"self": 0.0017919940000865608
}
}
},
"UnityEnvironment.step": {
"total": 0.04661205500019605,
"count": 1,
"is_parallel": true,
"self": 0.0005237610005224269,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046562599982280517,
"count": 1,
"is_parallel": true,
"self": 0.00046562599982280517
},
"communicator.exchange": {
"total": 0.04405437199989137,
"count": 1,
"is_parallel": true,
"self": 0.04405437199989137
},
"steps_from_proto": {
"total": 0.001568295999959446,
"count": 1,
"is_parallel": true,
"self": 0.00034167399962825584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00122662200033119,
"count": 8,
"is_parallel": true,
"self": 0.00122662200033119
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1267.6380562869929,
"count": 63525,
"is_parallel": true,
"self": 31.86575284097762,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.49096477305102,
"count": 63525,
"is_parallel": true,
"self": 22.49096477305102
},
"communicator.exchange": {
"total": 1118.8355695659245,
"count": 63525,
"is_parallel": true,
"self": 1118.8355695659245
},
"steps_from_proto": {
"total": 94.44576910703972,
"count": 63525,
"is_parallel": true,
"self": 18.941822960158788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.50394614688093,
"count": 508200,
"is_parallel": true,
"self": 75.50394614688093
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 677.1137661939797,
"count": 63526,
"self": 2.6668814119602757,
"children": {
"process_trajectory": {
"total": 125.4233934490212,
"count": 63526,
"self": 125.21716353602187,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20622991299933346,
"count": 2,
"self": 0.20622991299933346
}
}
},
"_update_policy": {
"total": 549.0234913329982,
"count": 454,
"self": 300.9290896259986,
"children": {
"TorchPPOOptimizer.update": {
"total": 248.09440170699963,
"count": 22752,
"self": 248.09440170699963
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.059999704011716e-06,
"count": 1,
"self": 1.059999704011716e-06
},
"TrainerController._save_models": {
"total": 0.08540032800010522,
"count": 1,
"self": 0.0012352459998510312,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08416508200025419,
"count": 1,
"self": 0.08416508200025419
}
}
}
}
}
}
}