agercas's picture
Upload first trained model
ed2fed6
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0324958562850952,
"min": 1.0324958562850952,
"max": 2.7362606525421143,
"count": 19
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9983.2021484375,
"min": 9983.2021484375,
"max": 27363.197265625,
"count": 19
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 19968.0,
"max": 199984.0,
"count": 19
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 19968.0,
"max": 199984.0,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.95816707611084,
"min": 1.6373494863510132,
"max": 12.974312782287598,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2656.42431640625,
"min": 240.69036865234375,
"max": 2656.42431640625,
"count": 19
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 19
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 6567.0,
"max": 10945.0,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0717159430592266,
"min": 0.06287369485025741,
"max": 0.0740596211179817,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.35857971529613303,
"min": 0.19122733085989202,
"max": 0.3702981055899085,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2412644263576059,
"min": 0.2023413633599001,
"max": 0.27574254169183615,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.2063221317880295,
"min": 0.6373675061097624,
"max": 1.3787127084591808,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.620097459999994e-06,
"min": 7.620097459999994e-06,
"max": 0.00027492000836,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.810048729999997e-05,
"min": 3.810048729999997e-05,
"max": 0.0013086000637999998,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10254,
"min": 0.10254,
"max": 0.19164,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5127,
"min": 0.42996,
"max": 0.9362,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001367459999999999,
"min": 0.0001367459999999999,
"max": 0.004582836000000001,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0006837299999999995,
"min": 0.0006837299999999995,
"max": 0.02181638,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.490909090909092,
"min": 6.484848484848484,
"max": 25.727272727272727,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1402.0,
"min": 214.0,
"max": 1415.0,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.490909090909092,
"min": 6.484848484848484,
"max": 25.727272727272727,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1402.0,
"min": 214.0,
"max": 1415.0,
"count": 19
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674302560",
"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 --resume ./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": "1674303048"
},
"total": 488.6566830529996,
"count": 1,
"self": 0.4860976830000254,
"children": {
"run_training.setup": {
"total": 0.12196756699995603,
"count": 1,
"self": 0.12196756699995603
},
"TrainerController.start_learning": {
"total": 488.0486178029996,
"count": 1,
"self": 0.7445246820293505,
"children": {
"TrainerController._reset_env": {
"total": 3.90459149399976,
"count": 1,
"self": 3.90459149399976
},
"TrainerController.advance": {
"total": 483.2644932999706,
"count": 17076,
"self": 0.39590634099340605,
"children": {
"env_step": {
"total": 482.8685869589772,
"count": 17076,
"self": 366.1014675770598,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.40416076195606,
"count": 17076,
"self": 1.9000043959708819,
"children": {
"TorchPolicy.evaluate": {
"total": 114.50415636598518,
"count": 17076,
"self": 18.748149814973203,
"children": {
"TorchPolicy.sample_actions": {
"total": 95.75600655101198,
"count": 17076,
"self": 95.75600655101198
}
}
}
}
},
"workers": {
"total": 0.3629586199613186,
"count": 17076,
"self": 0.0,
"children": {
"worker_root": {
"total": 486.4482358430241,
"count": 17076,
"is_parallel": true,
"self": 213.5691554780642,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030933350003579108,
"count": 1,
"is_parallel": true,
"self": 0.001209807001032459,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018835279993254517,
"count": 10,
"is_parallel": true,
"self": 0.0018835279993254517
}
}
},
"UnityEnvironment.step": {
"total": 0.05399533199988582,
"count": 1,
"is_parallel": true,
"self": 0.0007145740005398693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003218939996258996,
"count": 1,
"is_parallel": true,
"self": 0.0003218939996258996
},
"communicator.exchange": {
"total": 0.05041704599989316,
"count": 1,
"is_parallel": true,
"self": 0.05041704599989316
},
"steps_from_proto": {
"total": 0.0025418179998268897,
"count": 1,
"is_parallel": true,
"self": 0.0005484169996634591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019934010001634306,
"count": 10,
"is_parallel": true,
"self": 0.0019934010001634306
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 272.8790803649599,
"count": 17075,
"is_parallel": true,
"self": 10.912706739975874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.17792713100107,
"count": 17075,
"is_parallel": true,
"self": 6.17792713100107
},
"communicator.exchange": {
"total": 215.17583894198015,
"count": 17075,
"is_parallel": true,
"self": 215.17583894198015
},
"steps_from_proto": {
"total": 40.61260755200283,
"count": 17075,
"is_parallel": true,
"self": 8.531378088011934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.081229463990894,
"count": 170750,
"is_parallel": true,
"self": 32.081229463990894
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012147300003562123,
"count": 1,
"self": 0.00012147300003562123,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 479.1179705830027,
"count": 474755,
"is_parallel": true,
"self": 12.11899797596243,
"children": {
"process_trajectory": {
"total": 265.15417910203814,
"count": 474755,
"is_parallel": true,
"self": 264.22736496703874,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9268141349994039,
"count": 4,
"is_parallel": true,
"self": 0.9268141349994039
}
}
},
"_update_policy": {
"total": 201.84479350500214,
"count": 85,
"is_parallel": true,
"self": 50.2479304249905,
"children": {
"TorchPPOOptimizer.update": {
"total": 151.59686308001164,
"count": 4332,
"is_parallel": true,
"self": 151.59686308001164
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13488685399988753,
"count": 1,
"self": 0.0013829480003550998,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13350390599953244,
"count": 1,
"self": 0.13350390599953244
}
}
}
}
}
}
}