felipekataishi's picture
First training of SnowballTarget
4084251 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.924744725227356,
"min": 0.924744725227356,
"max": 2.8703043460845947,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8829.462890625,
"min": 8829.462890625,
"max": 29394.787109375,
"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": 12.855974197387695,
"min": 0.21560347080230713,
"max": 12.855974197387695,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2506.9150390625,
"min": 41.82707214355469,
"max": 2576.71923828125,
"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": 0.06443361980977808,
"min": 0.060618831289021353,
"max": 0.07280477282326377,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2577344792391123,
"min": 0.24247532515608541,
"max": 0.3640238641163188,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2050953002683088,
"min": 0.11815486539054809,
"max": 0.27296603799742813,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8203812010732352,
"min": 0.47261946156219237,
"max": 1.2028105320299372,
"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": 25.727272727272727,
"min": 3.090909090909091,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 136.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.090909090909091,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 136.0,
"max": 1378.0,
"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": "1722001773",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722002235"
},
"total": 461.579332669,
"count": 1,
"self": 0.431565513999999,
"children": {
"run_training.setup": {
"total": 0.05876114700004109,
"count": 1,
"self": 0.05876114700004109
},
"TrainerController.start_learning": {
"total": 461.08900600799996,
"count": 1,
"self": 0.5697685419980871,
"children": {
"TrainerController._reset_env": {
"total": 2.811624610000081,
"count": 1,
"self": 2.811624610000081
},
"TrainerController.advance": {
"total": 457.6099732650016,
"count": 18201,
"self": 0.2789235480018988,
"children": {
"env_step": {
"total": 457.3310497169997,
"count": 18201,
"self": 297.3553704979938,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.68732351300628,
"count": 18201,
"self": 1.5728544639995334,
"children": {
"TorchPolicy.evaluate": {
"total": 158.11446904900674,
"count": 18201,
"self": 158.11446904900674
}
}
},
"workers": {
"total": 0.28835570599960647,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.8436001009966,
"count": 18201,
"is_parallel": true,
"self": 232.53985221199628,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0070479199999908815,
"count": 1,
"is_parallel": true,
"self": 0.005137137000133407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019107829998574744,
"count": 10,
"is_parallel": true,
"self": 0.0019107829998574744
}
}
},
"UnityEnvironment.step": {
"total": 0.041373463000013544,
"count": 1,
"is_parallel": true,
"self": 0.0006981540001333997,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004057039999452172,
"count": 1,
"is_parallel": true,
"self": 0.0004057039999452172
},
"communicator.exchange": {
"total": 0.03809261499998229,
"count": 1,
"is_parallel": true,
"self": 0.03809261499998229
},
"steps_from_proto": {
"total": 0.0021769899999526388,
"count": 1,
"is_parallel": true,
"self": 0.00042704700001650053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017499429999361382,
"count": 10,
"is_parallel": true,
"self": 0.0017499429999361382
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.3037478890003,
"count": 18200,
"is_parallel": true,
"self": 10.332983565991299,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.459065445995066,
"count": 18200,
"is_parallel": true,
"self": 5.459065445995066
},
"communicator.exchange": {
"total": 177.14666577901028,
"count": 18200,
"is_parallel": true,
"self": 177.14666577901028
},
"steps_from_proto": {
"total": 34.365033098003664,
"count": 18200,
"is_parallel": true,
"self": 6.616863504991443,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.74816959301222,
"count": 182000,
"is_parallel": true,
"self": 27.74816959301222
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019500200005495572,
"count": 1,
"self": 0.00019500200005495572,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.2219469640057,
"count": 645479,
"is_parallel": true,
"self": 14.009926201047051,
"children": {
"process_trajectory": {
"total": 251.31737486895793,
"count": 645479,
"is_parallel": true,
"self": 250.47032377295795,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8470510959999729,
"count": 4,
"is_parallel": true,
"self": 0.8470510959999729
}
}
},
"_update_policy": {
"total": 186.89464589400075,
"count": 90,
"is_parallel": true,
"self": 58.427705528998445,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.4669403650023,
"count": 4587,
"is_parallel": true,
"self": 128.4669403650023
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09744458900013342,
"count": 1,
"self": 0.0009463320000122621,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09649825700012116,
"count": 1,
"self": 0.09649825700012116
}
}
}
}
}
}
}