ppo-Pyramid / run_logs /timers.json
Anant58's picture
First Push
c88bdef
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.49228137731552124,
"min": 0.4758806824684143,
"max": 1.4255006313323975,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14776.3173828125,
"min": 14268.806640625,
"max": 43243.98828125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989876.0,
"min": 29952.0,
"max": 989876.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989876.0,
"min": 29952.0,
"max": 989876.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5085049867630005,
"min": -0.09509684145450592,
"max": 0.5085049867630005,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 140.34738159179688,
"min": -22.8232421875,
"max": 140.34738159179688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 1.695114016532898,
"min": -0.7117506861686707,
"max": 1.695114016532898,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 467.8514709472656,
"min": -192.88442993164062,
"max": 467.8514709472656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0711860338611403,
"min": 0.06396258025225031,
"max": 0.07312517793987662,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9966044740559642,
"min": 0.501602817393355,
"max": 1.0906162025411523,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.2269248109529674,
"min": 0.0010670027417464232,
"max": 0.2269248109529674,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 3.1769473533415438,
"min": 0.014938038384449924,
"max": 3.1769473533415438,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.333833269707146e-06,
"min": 7.333833269707146e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010267366577590004,
"min": 0.00010267366577590004,
"max": 0.003507736430754599,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244457857142861,
"min": 0.10244457857142861,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4342241000000004,
"min": 1.3886848,
"max": 2.5692454000000007,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025421339928571434,
"min": 0.00025421339928571434,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003558987590000001,
"min": 0.003558987590000001,
"max": 0.11694761546,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013595799915492535,
"min": 0.013595799915492535,
"max": 0.521666407585144,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19034120440483093,
"min": 0.19034120440483093,
"max": 3.651664972305298,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 405.9620253164557,
"min": 367.8918918918919,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32071.0,
"min": 15984.0,
"max": 32710.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4927366893691352,
"min": -1.0000000521540642,
"max": 1.5510026770266327,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 117.92619846016169,
"min": -30.742001697421074,
"max": 117.92619846016169,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4927366893691352,
"min": -1.0000000521540642,
"max": 1.5510026770266327,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 117.92619846016169,
"min": -30.742001697421074,
"max": 117.92619846016169,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05688938951264195,
"min": 0.054377851231382356,
"max": 9.939922513440251,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.494261771498714,
"min": 4.023960991122294,
"max": 159.03876021504402,
"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": "1701244298",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1701246531"
},
"total": 2233.649016087,
"count": 1,
"self": 0.48798984599989126,
"children": {
"run_training.setup": {
"total": 0.05245500099999845,
"count": 1,
"self": 0.05245500099999845
},
"TrainerController.start_learning": {
"total": 2233.10857124,
"count": 1,
"self": 1.3845222170516536,
"children": {
"TrainerController._reset_env": {
"total": 3.1660953880000307,
"count": 1,
"self": 3.1660953880000307
},
"TrainerController.advance": {
"total": 2228.4753854989485,
"count": 63645,
"self": 1.462287500079583,
"children": {
"env_step": {
"total": 1587.0470386529744,
"count": 63645,
"self": 1451.5950304768141,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.59313354310189,
"count": 63645,
"self": 4.853877667112101,
"children": {
"TorchPolicy.evaluate": {
"total": 129.73925587598978,
"count": 62552,
"self": 129.73925587598978
}
}
},
"workers": {
"total": 0.858874633058349,
"count": 63645,
"self": 0.0,
"children": {
"worker_root": {
"total": 2228.085297202014,
"count": 63645,
"is_parallel": true,
"self": 899.8062385789644,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002179544000000533,
"count": 1,
"is_parallel": true,
"self": 0.0007327710002300591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014467729997704737,
"count": 8,
"is_parallel": true,
"self": 0.0014467729997704737
}
}
},
"UnityEnvironment.step": {
"total": 0.07050914899991767,
"count": 1,
"is_parallel": true,
"self": 0.0005980870000712457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005149629998868477,
"count": 1,
"is_parallel": true,
"self": 0.0005149629998868477
},
"communicator.exchange": {
"total": 0.0656836809998822,
"count": 1,
"is_parallel": true,
"self": 0.0656836809998822
},
"steps_from_proto": {
"total": 0.0037124180000773777,
"count": 1,
"is_parallel": true,
"self": 0.002384113000061916,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013283050000154617,
"count": 8,
"is_parallel": true,
"self": 0.0013283050000154617
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1328.2790586230494,
"count": 63644,
"is_parallel": true,
"self": 35.179826708027804,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.329501634008466,
"count": 63644,
"is_parallel": true,
"self": 25.329501634008466
},
"communicator.exchange": {
"total": 1165.647770069028,
"count": 63644,
"is_parallel": true,
"self": 1165.647770069028
},
"steps_from_proto": {
"total": 102.1219602119852,
"count": 63644,
"is_parallel": true,
"self": 20.642607923085052,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.47935228890015,
"count": 509152,
"is_parallel": true,
"self": 81.47935228890015
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 639.9660593458948,
"count": 63645,
"self": 2.620377552859736,
"children": {
"process_trajectory": {
"total": 131.37299407203227,
"count": 63645,
"self": 131.19531803803193,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17767603400034204,
"count": 2,
"self": 0.17767603400034204
}
}
},
"_update_policy": {
"total": 505.9726877210028,
"count": 448,
"self": 303.17608859704137,
"children": {
"TorchPPOOptimizer.update": {
"total": 202.7965991239614,
"count": 22785,
"self": 202.7965991239614
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.168999915535096e-06,
"count": 1,
"self": 1.168999915535096e-06
},
"TrainerController._save_models": {
"total": 0.08256696699982058,
"count": 1,
"self": 0.0012608779998117825,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0813060890000088,
"count": 1,
"self": 0.0813060890000088
}
}
}
}
}
}
}