ppo-Pyramids / run_logs /timers.json
erniechiew's picture
Just running the notebook
c3bb8ae
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.24597525596618652,
"min": 0.2403615266084671,
"max": 1.4664433002471924,
"count": 50
},
"Pyramids.Policy.Entropy.sum": {
"value": 7395.0,
"min": 7207.0,
"max": 44486.0234375,
"count": 50
},
"Pyramids.Step.mean": {
"value": 1499881.0,
"min": 29952.0,
"max": 1499881.0,
"count": 50
},
"Pyramids.Step.sum": {
"value": 1499881.0,
"min": 29952.0,
"max": 1499881.0,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.696268618106842,
"min": -0.14053799211978912,
"max": 0.696268618106842,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 202.61416625976562,
"min": -33.30750274658203,
"max": 202.61416625976562,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01638094335794449,
"min": -0.0046220882795751095,
"max": 0.329357773065567,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.766854763031006,
"min": -1.192498803138733,
"max": 78.05779266357422,
"count": 50
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06489497362746902,
"min": 0.06264212223899361,
"max": 0.07354319610680078,
"count": 50
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9085296307845662,
"min": 0.5048474687397154,
"max": 1.066189969239834,
"count": 50
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015031521098405524,
"min": 0.0009610743752965195,
"max": 0.017585090033934027,
"count": 50
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21044129537767733,
"min": 0.013455041254151272,
"max": 0.25705713322774193,
"count": 50
},
"Pyramids.Policy.LearningRate.mean": {
"value": 3.0150847092904756e-06,
"min": 3.0150847092904756e-06,
"max": 0.00029676708679192377,
"count": 50
},
"Pyramids.Policy.LearningRate.sum": {
"value": 4.221118593006666e-05,
"min": 4.221118593006666e-05,
"max": 0.003628664290445267,
"count": 50
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10100499523809525,
"min": 0.10100499523809525,
"max": 0.19892236190476195,
"count": 50
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4140699333333335,
"min": 1.3924565333333336,
"max": 2.5903810666666667,
"count": 50
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00011039902428571427,
"min": 0.00011039902428571427,
"max": 0.009892343954285714,
"count": 50
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0015455863399999998,
"min": 0.0015455863399999998,
"max": 0.12096451786000002,
"count": 50
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008541652001440525,
"min": 0.008315244689583778,
"max": 0.5376355648040771,
"count": 50
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1195831224322319,
"min": 0.1164134293794632,
"max": 3.76344895362854,
"count": 50
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 253.9189189189189,
"min": 253.9189189189189,
"max": 999.0,
"count": 50
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28185.0,
"min": 15984.0,
"max": 33073.0,
"count": 50
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7100378195713233,
"min": -1.0000000521540642,
"max": 1.7100378195713233,
"count": 50
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 189.81419797241688,
"min": -30.07520167529583,
"max": 189.81419797241688,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7100378195713233,
"min": -1.0000000521540642,
"max": 1.7100378195713233,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 189.81419797241688,
"min": -30.07520167529583,
"max": 189.81419797241688,
"count": 50
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02234050209950215,
"min": 0.02234050209950215,
"max": 10.665581804700196,
"count": 50
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.479795733044739,
"min": 2.4578695568052353,
"max": 170.64930887520313,
"count": 50
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675660628",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675663824"
},
"total": 3195.761814095,
"count": 1,
"self": 0.4278418039993994,
"children": {
"run_training.setup": {
"total": 0.10553459600009774,
"count": 1,
"self": 0.10553459600009774
},
"TrainerController.start_learning": {
"total": 3195.228437695,
"count": 1,
"self": 1.9381409399343283,
"children": {
"TrainerController._reset_env": {
"total": 5.904973448999954,
"count": 1,
"self": 5.904973448999954
},
"TrainerController.advance": {
"total": 3187.2979305610656,
"count": 96273,
"self": 2.0747172750557183,
"children": {
"env_step": {
"total": 2217.348461175957,
"count": 96273,
"self": 2057.082679788957,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.09035007893954,
"count": 96273,
"self": 6.650497732832491,
"children": {
"TorchPolicy.evaluate": {
"total": 152.43985234610705,
"count": 93809,
"self": 51.61167028711884,
"children": {
"TorchPolicy.sample_actions": {
"total": 100.8281820589882,
"count": 93809,
"self": 100.8281820589882
}
}
}
}
},
"workers": {
"total": 1.1754313080600696,
"count": 96273,
"self": 0.0,
"children": {
"worker_root": {
"total": 3187.9781063958853,
"count": 96273,
"is_parallel": true,
"self": 1284.7106134639669,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00285074699991128,
"count": 1,
"is_parallel": true,
"self": 0.00088325799993072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00196748899998056,
"count": 8,
"is_parallel": true,
"self": 0.00196748899998056
}
}
},
"UnityEnvironment.step": {
"total": 0.04499545299995589,
"count": 1,
"is_parallel": true,
"self": 0.0004641549999178096,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004934879998472752,
"count": 1,
"is_parallel": true,
"self": 0.0004934879998472752
},
"communicator.exchange": {
"total": 0.042388733000052525,
"count": 1,
"is_parallel": true,
"self": 0.042388733000052525
},
"steps_from_proto": {
"total": 0.001649077000138277,
"count": 1,
"is_parallel": true,
"self": 0.00041630700047790015,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001232769999660377,
"count": 8,
"is_parallel": true,
"self": 0.001232769999660377
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1903.2674929319185,
"count": 96272,
"is_parallel": true,
"self": 41.47352784192822,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 34.329195338021464,
"count": 96272,
"is_parallel": true,
"self": 34.329195338021464
},
"communicator.exchange": {
"total": 1672.551338576024,
"count": 96272,
"is_parallel": true,
"self": 1672.551338576024
},
"steps_from_proto": {
"total": 154.91343117594488,
"count": 96272,
"is_parallel": true,
"self": 34.60206976907534,
"children": {
"_process_rank_one_or_two_observation": {
"total": 120.31136140686954,
"count": 770176,
"is_parallel": true,
"self": 120.31136140686954
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 967.8747521100531,
"count": 96273,
"self": 3.622528000061493,
"children": {
"process_trajectory": {
"total": 223.74608655798647,
"count": 96273,
"self": 223.4640545159864,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2820320420000826,
"count": 3,
"self": 0.2820320420000826
}
}
},
"_update_policy": {
"total": 740.5061375520052,
"count": 690,
"self": 277.18348833500954,
"children": {
"TorchPPOOptimizer.update": {
"total": 463.3226492169956,
"count": 34161,
"self": 463.3226492169956
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.184000211651437e-06,
"count": 1,
"self": 1.184000211651437e-06
},
"TrainerController._save_models": {
"total": 0.087391561000004,
"count": 1,
"self": 0.0016764459996920777,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08571511500031193,
"count": 1,
"self": 0.08571511500031193
}
}
}
}
}
}
}