daripaez's picture
First training
cd56f87
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8838948011398315,
"min": 0.865014374256134,
"max": 2.8627073764801025,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8740.8359375,
"min": 8601.703125,
"max": 29254.0078125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9984.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9984.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.108009338378906,
"min": 0.2657057046890259,
"max": 13.108009338378906,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 4535.37109375,
"min": 91.66847229003906,
"max": 4622.240234375,
"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": 0.07234310498917658,
"min": 0.0618531605234203,
"max": 0.07515793920805056,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2893724199567063,
"min": 0.2474126420936812,
"max": 0.3757896960402528,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16026489787241993,
"min": 0.05984287236031949,
"max": 0.22478236835084708,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6410595914896797,
"min": 0.23937148944127795,
"max": 1.0767931789159775,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.977272727272727,
"min": 2.477272727272727,
"max": 26.10909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1143.0,
"min": 109.0,
"max": 1436.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.977272727272727,
"min": 2.477272727272727,
"max": 26.10909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1143.0,
"min": 109.0,
"max": 1436.0,
"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": "1674055128",
"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=SnowballTarget_1 --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": "1674055553"
},
"total": 424.68131394499983,
"count": 1,
"self": 0.3912004670000897,
"children": {
"run_training.setup": {
"total": 0.10268004999988989,
"count": 1,
"self": 0.10268004999988989
},
"TrainerController.start_learning": {
"total": 424.18743342799985,
"count": 1,
"self": 0.5198055790090166,
"children": {
"TrainerController._reset_env": {
"total": 9.180593180000187,
"count": 1,
"self": 9.180593180000187
},
"TrainerController.advance": {
"total": 414.36454989599065,
"count": 18202,
"self": 0.25021452399346344,
"children": {
"env_step": {
"total": 414.1143353719972,
"count": 18202,
"self": 284.88209192302133,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.97490898498063,
"count": 18202,
"self": 1.4300724509787415,
"children": {
"TorchPolicy.evaluate": {
"total": 127.54483653400189,
"count": 18202,
"self": 29.94204236600649,
"children": {
"TorchPolicy.sample_actions": {
"total": 97.6027941679954,
"count": 18202,
"self": 97.6027941679954
}
}
}
}
},
"workers": {
"total": 0.2573344639952211,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.0528317659978,
"count": 18202,
"is_parallel": true,
"self": 209.3324036649933,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007179860000178451,
"count": 1,
"is_parallel": true,
"self": 0.0039705989997855795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003209261000392871,
"count": 10,
"is_parallel": true,
"self": 0.003209261000392871
}
}
},
"UnityEnvironment.step": {
"total": 0.0446534679999786,
"count": 1,
"is_parallel": true,
"self": 0.0005432119996839901,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00027205400010643643,
"count": 1,
"is_parallel": true,
"self": 0.00027205400010643643
},
"communicator.exchange": {
"total": 0.04224320400021497,
"count": 1,
"is_parallel": true,
"self": 0.04224320400021497
},
"steps_from_proto": {
"total": 0.0015949979999732022,
"count": 1,
"is_parallel": true,
"self": 0.00038038599973333476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012146120002398675,
"count": 10,
"is_parallel": true,
"self": 0.0012146120002398675
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.72042810100447,
"count": 18201,
"is_parallel": true,
"self": 8.145644615019364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.75768895899364,
"count": 18201,
"is_parallel": true,
"self": 4.75768895899364
},
"communicator.exchange": {
"total": 171.9413617049936,
"count": 18201,
"is_parallel": true,
"self": 171.9413617049936
},
"steps_from_proto": {
"total": 28.87573282199787,
"count": 18201,
"is_parallel": true,
"self": 6.195891647034614,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.679841174963258,
"count": 182010,
"is_parallel": true,
"self": 22.679841174963258
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.306000005271926e-05,
"count": 1,
"self": 4.306000005271926e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 410.9586865989147,
"count": 384045,
"is_parallel": true,
"self": 10.230067670001063,
"children": {
"process_trajectory": {
"total": 279.438332482913,
"count": 384045,
"is_parallel": true,
"self": 278.70274620991313,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7355862729998535,
"count": 4,
"is_parallel": true,
"self": 0.7355862729998535
}
}
},
"_update_policy": {
"total": 121.29028644600066,
"count": 90,
"is_parallel": true,
"self": 39.144873217007216,
"children": {
"TorchPPOOptimizer.update": {
"total": 82.14541322899345,
"count": 4587,
"is_parallel": true,
"self": 82.14541322899345
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12244171299994377,
"count": 1,
"self": 0.000825394999992568,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1216163179999512,
"count": 1,
"self": 0.1216163179999512
}
}
}
}
}
}
}