crossroderick's picture
First training of SnowballTarget
4c9f1a6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5547086000442505,
"min": 0.5157235860824585,
"max": 2.8668413162231445,
"count": 200
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5717.3818359375,
"min": 4992.2041015625,
"max": 29390.857421875,
"count": 200
},
"SnowballTarget.Step.mean": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Step.sum": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.375473976135254,
"min": 0.3523101508617401,
"max": 14.525879859924316,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2946.97216796875,
"min": 68.3481674194336,
"max": 2963.279541015625,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07180224177747162,
"min": 0.06116235598514608,
"max": 0.07791459801271285,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3590112088873581,
"min": 0.2446494239405843,
"max": 0.37389705292612324,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.14252558046696234,
"min": 0.10585807529323753,
"max": 0.28417206365688175,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7126279023348117,
"min": 0.4234323011729501,
"max": 1.3991894196061527,
"count": 200
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032997656000039e-07,
"min": 7.032997656000039e-07,
"max": 0.00029918820027059994,
"count": 200
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5164988280000196e-06,
"min": 3.5164988280000196e-06,
"max": 0.0014885160038279998,
"count": 200
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10023440000000002,
"min": 0.10023440000000002,
"max": 0.1997294,
"count": 200
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5011720000000001,
"min": 0.4029176,
"max": 0.996172,
"count": 200
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.1696560000000067e-05,
"min": 2.1696560000000067e-05,
"max": 0.004986497059999999,
"count": 200
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00010848280000000034,
"min": 0.00010848280000000034,
"max": 0.024808982800000004,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.927272727272726,
"min": 3.25,
"max": 28.545454545454547,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1536.0,
"min": 143.0,
"max": 1570.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.927272727272726,
"min": 3.25,
"max": 28.545454545454547,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1536.0,
"min": 143.0,
"max": 1570.0,
"count": 200
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709674778",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/home/rodrigopc/.local/bin/mlagents-learn SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.app --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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709678563"
},
"total": 3785.2340286299986,
"count": 1,
"self": 0.42197561300054076,
"children": {
"run_training.setup": {
"total": 0.046305935000418685,
"count": 1,
"self": 0.046305935000418685
},
"TrainerController.start_learning": {
"total": 3784.7657470819977,
"count": 1,
"self": 4.373204207415256,
"children": {
"TrainerController._reset_env": {
"total": 3.107422298999154,
"count": 1,
"self": 3.107422298999154
},
"TrainerController.advance": {
"total": 3777.206958249586,
"count": 181872,
"self": 2.371795165414369,
"children": {
"env_step": {
"total": 3774.8351630841717,
"count": 181872,
"self": 2778.077039207892,
"children": {
"SubprocessEnvManager._take_step": {
"total": 994.412009872045,
"count": 181872,
"self": 13.988687092733016,
"children": {
"TorchPolicy.evaluate": {
"total": 980.423322779312,
"count": 181872,
"self": 980.423322779312
}
}
},
"workers": {
"total": 2.3461140042345505,
"count": 181872,
"self": 0.0,
"children": {
"worker_root": {
"total": 3778.960501090598,
"count": 181872,
"is_parallel": true,
"self": 1600.2780851432944,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002517222001188202,
"count": 1,
"is_parallel": true,
"self": 0.0005590100081462879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001958211993041914,
"count": 10,
"is_parallel": true,
"self": 0.001958211993041914
}
}
},
"UnityEnvironment.step": {
"total": 0.0275184710008034,
"count": 1,
"is_parallel": true,
"self": 0.0006014729988237377,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003588450017559808,
"count": 1,
"is_parallel": true,
"self": 0.0003588450017559808
},
"communicator.exchange": {
"total": 0.02480688099967665,
"count": 1,
"is_parallel": true,
"self": 0.02480688099967665
},
"steps_from_proto": {
"total": 0.0017512720005470328,
"count": 1,
"is_parallel": true,
"self": 0.00033090600118157454,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014203659993654583,
"count": 10,
"is_parallel": true,
"self": 0.0014203659993654583
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2178.6824159473035,
"count": 181871,
"is_parallel": true,
"self": 92.92088599702038,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 53.80016340460861,
"count": 181871,
"is_parallel": true,
"self": 53.80016340460861
},
"communicator.exchange": {
"total": 1775.348745384279,
"count": 181871,
"is_parallel": true,
"self": 1775.348745384279
},
"steps_from_proto": {
"total": 256.6126211613955,
"count": 181871,
"is_parallel": true,
"self": 47.73723850035822,
"children": {
"_process_rank_one_or_two_observation": {
"total": 208.8753826610373,
"count": 1818710,
"is_parallel": true,
"self": 208.8753826610373
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0003874749963870272,
"count": 1,
"self": 0.0003874749963870272,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 3748.6489063267836,
"count": 4284829,
"is_parallel": true,
"self": 76.67259495955295,
"children": {
"process_trajectory": {
"total": 2068.6670503342248,
"count": 4284829,
"is_parallel": true,
"self": 2064.5999245492058,
"children": {
"RLTrainer._checkpoint": {
"total": 4.067125785019016,
"count": 40,
"is_parallel": true,
"self": 4.067125785019016
}
}
},
"_update_policy": {
"total": 1603.309261033006,
"count": 909,
"is_parallel": true,
"self": 318.34363177923296,
"children": {
"TorchPPOOptimizer.update": {
"total": 1284.965629253773,
"count": 46356,
"is_parallel": true,
"self": 1284.965629253773
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07777485100086778,
"count": 1,
"self": 0.0012268869977560826,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0765479640031117,
"count": 1,
"self": 0.0765479640031117
}
}
}
}
}
}
}