zipbomb's picture
First training of SnowballTarget
94e0350
raw
history blame contribute delete
No virus
19 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9240750074386597,
"min": 0.9223202466964722,
"max": 2.8620798587799072,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8823.068359375,
"min": 8823.068359375,
"max": 29342.04296875,
"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": 12.306697845458984,
"min": 0.3830091655254364,
"max": 12.306697845458984,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2399.80615234375,
"min": 74.30377960205078,
"max": 2455.365966796875,
"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": 0.0644589486118646,
"min": 0.061666330814535056,
"max": 0.07989270191619119,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2578357944474584,
"min": 0.24666532325814022,
"max": 0.3586139523095506,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23694027018021135,
"min": 0.12905863717691424,
"max": 0.28227439674676635,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9477610807208454,
"min": 0.516234548707657,
"max": 1.4113719837338317,
"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": 25.295454545454547,
"min": 3.4545454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 152.0,
"max": 1345.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.4545454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 152.0,
"max": 1345.0,
"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": "1673717113",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673717572"
},
"total": 458.60244680000005,
"count": 1,
"self": 0.38972522400013077,
"children": {
"run_training.setup": {
"total": 0.11576358000002074,
"count": 1,
"self": 0.11576358000002074
},
"TrainerController.start_learning": {
"total": 458.0969579959999,
"count": 1,
"self": 0.5639222689826511,
"children": {
"TrainerController._reset_env": {
"total": 10.159732105999865,
"count": 1,
"self": 10.159732105999865
},
"TrainerController.advance": {
"total": 447.2499368610172,
"count": 18203,
"self": 0.30724800101938854,
"children": {
"env_step": {
"total": 446.9426888599978,
"count": 18203,
"self": 291.6251886000164,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.0283402079972,
"count": 18203,
"self": 1.4598852299768623,
"children": {
"TorchPolicy.evaluate": {
"total": 153.56845497802033,
"count": 18203,
"self": 33.94824812801676,
"children": {
"TorchPolicy.sample_actions": {
"total": 119.62020685000357,
"count": 18203,
"self": 119.62020685000357
}
}
}
}
},
"workers": {
"total": 0.2891600519842541,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.7822979189966,
"count": 18203,
"is_parallel": true,
"self": 223.34117047599443,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006223723999937647,
"count": 1,
"is_parallel": true,
"self": 0.003552266999577114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002671457000360533,
"count": 10,
"is_parallel": true,
"self": 0.002671457000360533
}
}
},
"UnityEnvironment.step": {
"total": 0.047435722000045644,
"count": 1,
"is_parallel": true,
"self": 0.000471709999601444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002968040000723704,
"count": 1,
"is_parallel": true,
"self": 0.0002968040000723704
},
"communicator.exchange": {
"total": 0.044798103000175615,
"count": 1,
"is_parallel": true,
"self": 0.044798103000175615
},
"steps_from_proto": {
"total": 0.001869105000196214,
"count": 1,
"is_parallel": true,
"self": 0.0004724139998870669,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001396691000309147,
"count": 10,
"is_parallel": true,
"self": 0.001396691000309147
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.4411274430022,
"count": 18202,
"is_parallel": true,
"self": 8.923359918992446,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.59295097600625,
"count": 18202,
"is_parallel": true,
"self": 5.59295097600625
},
"communicator.exchange": {
"total": 185.18888988500362,
"count": 18202,
"is_parallel": true,
"self": 185.18888988500362
},
"steps_from_proto": {
"total": 33.73592666299987,
"count": 18202,
"is_parallel": true,
"self": 7.2949312939576885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.440995369042184,
"count": 182020,
"is_parallel": true,
"self": 26.440995369042184
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0005611270000827062,
"count": 1,
"self": 0.0005611270000827062,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.91184225104325,
"count": 354317,
"is_parallel": true,
"self": 10.316784172007374,
"children": {
"process_trajectory": {
"total": 254.08473035403517,
"count": 354317,
"is_parallel": true,
"self": 253.30914219503507,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7755881590001081,
"count": 4,
"is_parallel": true,
"self": 0.7755881590001081
}
}
},
"_update_policy": {
"total": 179.5103277250007,
"count": 90,
"is_parallel": true,
"self": 45.099413607004635,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.41091411799607,
"count": 4584,
"is_parallel": true,
"self": 134.41091411799607
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12280563300009817,
"count": 1,
"self": 0.0008049079999636888,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12200072500013448,
"count": 1,
"self": 0.12200072500013448
}
}
}
}
}
}
}