ppo-Snowball / run_logs /timers.json
Beegbrain's picture
First push
1029f12
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8370588421821594,
"min": 0.8370588421821594,
"max": 2.8542063236236572,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8001.4453125,
"min": 8001.4453125,
"max": 29229.92578125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.270687103271484,
"min": 0.3743959367275238,
"max": 13.270687103271484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2587.783935546875,
"min": 72.6328125,
"max": 2680.736328125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0667861311642542,
"min": 0.06408279388209956,
"max": 0.07503892971376712,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2671445246570168,
"min": 0.25633117552839824,
"max": 0.35178090803092343,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1812143017702243,
"min": 0.1163729392711128,
"max": 0.2750221583773108,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7248572070808972,
"min": 0.4654917570844512,
"max": 1.347502407080987,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.431818181818183,
"min": 3.477272727272727,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1163.0,
"min": 153.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.431818181818183,
"min": 3.477272727272727,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1163.0,
"min": 153.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675610602",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1675611067"
},
"total": 465.2427168659999,
"count": 1,
"self": 0.38919790499994633,
"children": {
"run_training.setup": {
"total": 0.0999602379999942,
"count": 1,
"self": 0.0999602379999942
},
"TrainerController.start_learning": {
"total": 464.75355872299997,
"count": 1,
"self": 0.4810203889949207,
"children": {
"TrainerController._reset_env": {
"total": 9.441542031999916,
"count": 1,
"self": 9.441542031999916
},
"TrainerController.advance": {
"total": 454.7069577850052,
"count": 18202,
"self": 0.24432561801336306,
"children": {
"env_step": {
"total": 454.46263216699185,
"count": 18202,
"self": 316.41070745497484,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.80391107698858,
"count": 18202,
"self": 1.310673067992866,
"children": {
"TorchPolicy.evaluate": {
"total": 136.49323800899572,
"count": 18202,
"self": 31.371554670018327,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.12168333897739,
"count": 18202,
"self": 105.12168333897739
}
}
}
}
},
"workers": {
"total": 0.24801363502842833,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.6436276260017,
"count": 18202,
"is_parallel": true,
"self": 253.07267619502204,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009333385999980237,
"count": 1,
"is_parallel": true,
"self": 0.004150804999994762,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0051825809999854755,
"count": 10,
"is_parallel": true,
"self": 0.0051825809999854755
}
}
},
"UnityEnvironment.step": {
"total": 0.03300163500000508,
"count": 1,
"is_parallel": true,
"self": 0.0005004190001045572,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002917629999501514,
"count": 1,
"is_parallel": true,
"self": 0.0002917629999501514
},
"communicator.exchange": {
"total": 0.030231839999942167,
"count": 1,
"is_parallel": true,
"self": 0.030231839999942167
},
"steps_from_proto": {
"total": 0.001977613000008205,
"count": 1,
"is_parallel": true,
"self": 0.0004754599999614584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015021530000467465,
"count": 10,
"is_parallel": true,
"self": 0.0015021530000467465
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.57095143097968,
"count": 18201,
"is_parallel": true,
"self": 8.066219149960602,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.659429013017416,
"count": 18201,
"is_parallel": true,
"self": 4.659429013017416
},
"communicator.exchange": {
"total": 169.4974887249865,
"count": 18201,
"is_parallel": true,
"self": 169.4974887249865
},
"steps_from_proto": {
"total": 28.347814543015147,
"count": 18201,
"is_parallel": true,
"self": 5.950530731011554,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.397283812003593,
"count": 182010,
"is_parallel": true,
"self": 22.397283812003593
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.035200004182116e-05,
"count": 1,
"self": 4.035200004182116e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 451.9709286150445,
"count": 327152,
"is_parallel": true,
"self": 8.435361040063754,
"children": {
"process_trajectory": {
"total": 229.3675152119805,
"count": 327152,
"is_parallel": true,
"self": 228.62211618298,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7453990290005095,
"count": 4,
"is_parallel": true,
"self": 0.7453990290005095
}
}
},
"_update_policy": {
"total": 214.16805236300024,
"count": 90,
"is_parallel": true,
"self": 64.24910758399585,
"children": {
"TorchPPOOptimizer.update": {
"total": 149.9189447790044,
"count": 7645,
"is_parallel": true,
"self": 149.9189447790044
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12399816499987537,
"count": 1,
"self": 0.0009810970000216912,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12301706799985368,
"count": 1,
"self": 0.12301706799985368
}
}
}
}
}
}
}