LuniLand's picture
First training of SnowballTarget
dab1c51
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8144237399101257,
"min": 0.8144237399101257,
"max": 2.864283800125122,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7811.95263671875,
"min": 7811.95263671875,
"max": 29364.63671875,
"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": 12.940800666809082,
"min": 0.4891510009765625,
"max": 12.940800666809082,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.4560546875,
"min": 94.89529418945312,
"max": 2616.7109375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06621943149501948,
"min": 0.06106742003147362,
"max": 0.07501891057358544,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2648777259800779,
"min": 0.25995758873628516,
"max": 0.3662672878354879,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18095476341013816,
"min": 0.1246006164092607,
"max": 0.26170354900406856,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7238190536405527,
"min": 0.4984024656370428,
"max": 1.308517745020343,
"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": 26.136363636363637,
"min": 3.6136363636363638,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1150.0,
"min": 159.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.136363636363637,
"min": 3.6136363636363638,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1150.0,
"min": 159.0,
"max": 1392.0,
"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": "1678992664",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1678993180"
},
"total": 515.556439609,
"count": 1,
"self": 0.7015581619999693,
"children": {
"run_training.setup": {
"total": 0.11427148100000295,
"count": 1,
"self": 0.11427148100000295
},
"TrainerController.start_learning": {
"total": 514.740609966,
"count": 1,
"self": 0.6204927480041533,
"children": {
"TrainerController._reset_env": {
"total": 10.29433125700001,
"count": 1,
"self": 10.29433125700001
},
"TrainerController.advance": {
"total": 503.5982992399958,
"count": 18210,
"self": 0.31819355799484583,
"children": {
"env_step": {
"total": 503.28010568200096,
"count": 18210,
"self": 361.8207149290078,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.15267294900002,
"count": 18210,
"self": 2.654427113003976,
"children": {
"TorchPolicy.evaluate": {
"total": 138.49824583599604,
"count": 18210,
"self": 138.49824583599604
}
}
},
"workers": {
"total": 0.30671780399313775,
"count": 18210,
"self": 0.0,
"children": {
"worker_root": {
"total": 512.8655862550089,
"count": 18210,
"is_parallel": true,
"self": 245.72979510501142,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005216372000006686,
"count": 1,
"is_parallel": true,
"self": 0.003588868999997885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016275030000088009,
"count": 10,
"is_parallel": true,
"self": 0.0016275030000088009
}
}
},
"UnityEnvironment.step": {
"total": 0.06871063900001673,
"count": 1,
"is_parallel": true,
"self": 0.0005875449999734883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040380300004017045,
"count": 1,
"is_parallel": true,
"self": 0.00040380300004017045
},
"communicator.exchange": {
"total": 0.06529681000000664,
"count": 1,
"is_parallel": true,
"self": 0.06529681000000664
},
"steps_from_proto": {
"total": 0.0024224809999964236,
"count": 1,
"is_parallel": true,
"self": 0.0005552579998493457,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001867223000147078,
"count": 10,
"is_parallel": true,
"self": 0.001867223000147078
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 267.1357911499975,
"count": 18209,
"is_parallel": true,
"self": 10.537611372014624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.838865397997267,
"count": 18209,
"is_parallel": true,
"self": 5.838865397997267
},
"communicator.exchange": {
"total": 214.58367055899004,
"count": 18209,
"is_parallel": true,
"self": 214.58367055899004
},
"steps_from_proto": {
"total": 36.17564382099556,
"count": 18209,
"is_parallel": true,
"self": 7.306413234961099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.869230586034462,
"count": 182090,
"is_parallel": true,
"self": 28.869230586034462
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013032699996529118,
"count": 1,
"self": 0.00013032699996529118,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 499.5342581710448,
"count": 450493,
"is_parallel": true,
"self": 11.83451321106719,
"children": {
"process_trajectory": {
"total": 279.073494459978,
"count": 450493,
"is_parallel": true,
"self": 277.5261265169781,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5473679429999265,
"count": 4,
"is_parallel": true,
"self": 1.5473679429999265
}
}
},
"_update_policy": {
"total": 208.62625049999963,
"count": 90,
"is_parallel": true,
"self": 76.35642124399368,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.26982925600595,
"count": 4587,
"is_parallel": true,
"self": 132.26982925600595
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22735639400002583,
"count": 1,
"self": 0.0011255529999516511,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22623084100007418,
"count": 1,
"self": 0.22623084100007418
}
}
}
}
}
}
}