ppo-pyramids / run_logs /timers.json
jtan4albany's picture
First Push
bda9f8a verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.5378978252410889,
"min": 1.5278986692428589,
"max": 1.609351396560669,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 15157.5205078125,
"min": 15058.96875,
"max": 16479.7578125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 999936.0,
"min": 9984.0,
"max": 999936.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 999936.0,
"min": 9984.0,
"max": 999936.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.09972458332777023,
"min": -0.10215860605239868,
"max": -0.07824378460645676,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -16.15538215637207,
"min": -16.58575439453125,
"max": -12.206029891967773,
"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
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.025093469571209316,
"min": 0.018133621295970497,
"max": 0.031738389156420126,
"count": 90
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.025093469571209316,
"min": 0.018133621295970497,
"max": 0.031738389156420126,
"count": 90
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 1.809035160421803e-05,
"min": 5.550883073131748e-06,
"max": 0.006510537752712315,
"count": 90
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 1.809035160421803e-05,
"min": 5.550883073131748e-06,
"max": 0.006510537752712315,
"count": 90
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.8992990336000014e-06,
"min": 2.8992990336000014e-06,
"max": 0.00029662080112639996,
"count": 90
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.8992990336000014e-06,
"min": 2.8992990336000014e-06,
"max": 0.00029662080112639996,
"count": 90
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10096640000000001,
"min": 0.10096640000000001,
"max": 0.1988736,
"count": 90
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.10096640000000001,
"min": 0.10096640000000001,
"max": 0.1988736,
"count": 90
},
"Pyramids.Policy.Beta.mean": {
"value": 5.822336000000003e-05,
"min": 5.822336000000003e-05,
"max": 0.00494379264,
"count": 90
},
"Pyramids.Policy.Beta.sum": {
"value": 5.822336000000003e-05,
"min": 5.822336000000003e-05,
"max": 0.00494379264,
"count": 90
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 62
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 15984.0,
"min": 15984.0,
"max": 15984.0,
"count": 62
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000447034836,
"min": -1.0000000447034836,
"max": -1.0000000447034836,
"count": 74
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -16.000000715255737,
"min": -16.000000715255737,
"max": -1.0000000447034836,
"count": 74
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000447034836,
"min": -1.0000000447034836,
"max": -1.0000000447034836,
"count": 74
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -16.000000715255737,
"min": -16.000000715255737,
"max": -1.0000000447034836,
"count": 74
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1747318268",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747320242"
},
"total": 1973.8309908570004,
"count": 1,
"self": 0.6402728550001484,
"children": {
"run_training.setup": {
"total": 0.04058445700002267,
"count": 1,
"self": 0.04058445700002267
},
"TrainerController.start_learning": {
"total": 1973.1501335450002,
"count": 1,
"self": 2.3691229479577487,
"children": {
"TrainerController._reset_env": {
"total": 3.7067937139995593,
"count": 1,
"self": 3.7067937139995593
},
"TrainerController.advance": {
"total": 1967.0328599580434,
"count": 62512,
"self": 2.5801423180837446,
"children": {
"env_step": {
"total": 1508.154041063025,
"count": 62512,
"self": 1374.6545014929047,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.158958097104,
"count": 62512,
"self": 6.8851808781005275,
"children": {
"TorchPolicy.evaluate": {
"total": 125.27377721900348,
"count": 62512,
"self": 125.27377721900348
}
}
},
"workers": {
"total": 1.3405814730163002,
"count": 62512,
"self": 0.0,
"children": {
"worker_root": {
"total": 1966.2369547890871,
"count": 62512,
"is_parallel": true,
"self": 761.0536625339682,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002716659000270738,
"count": 1,
"is_parallel": true,
"self": 0.0007969930002218462,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019196660000488919,
"count": 8,
"is_parallel": true,
"self": 0.0019196660000488919
}
}
},
"UnityEnvironment.step": {
"total": 0.06636168099976203,
"count": 1,
"is_parallel": true,
"self": 0.0006437079996430839,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007503219999307476,
"count": 1,
"is_parallel": true,
"self": 0.0007503219999307476
},
"communicator.exchange": {
"total": 0.06308538100029182,
"count": 1,
"is_parallel": true,
"self": 0.06308538100029182
},
"steps_from_proto": {
"total": 0.0018822699998963799,
"count": 1,
"is_parallel": true,
"self": 0.00039052499960234854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014917450002940313,
"count": 8,
"is_parallel": true,
"self": 0.0014917450002940313
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1205.1832922551189,
"count": 62511,
"is_parallel": true,
"self": 43.612485362029474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 29.79853468794363,
"count": 62511,
"is_parallel": true,
"self": 29.79853468794363
},
"communicator.exchange": {
"total": 1008.2300185980566,
"count": 62511,
"is_parallel": true,
"self": 1008.2300185980566
},
"steps_from_proto": {
"total": 123.54225360708915,
"count": 62511,
"is_parallel": true,
"self": 26.18475538622579,
"children": {
"_process_rank_one_or_two_observation": {
"total": 97.35749822086336,
"count": 500088,
"is_parallel": true,
"self": 97.35749822086336
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 456.29867657693467,
"count": 62512,
"self": 2.93254959611113,
"children": {
"process_trajectory": {
"total": 130.12172531682745,
"count": 62512,
"self": 129.9364493208268,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18527599600065514,
"count": 2,
"self": 0.18527599600065514
}
}
},
"_update_policy": {
"total": 323.2444016639961,
"count": 90,
"self": 228.0752446119891,
"children": {
"TorchPPOOptimizer.update": {
"total": 95.169157052007,
"count": 2787,
"self": 95.169157052007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1319998520775698e-06,
"count": 1,
"self": 1.1319998520775698e-06
},
"TrainerController._save_models": {
"total": 0.04135579299963865,
"count": 1,
"self": 0.0006227189996934612,
"children": {
"RLTrainer._checkpoint": {
"total": 0.04073307399994519,
"count": 1,
"self": 0.04073307399994519
}
}
}
}
}
}
}