RL-5 / run_logs /timers.json
aadickk's picture
First Push
a4cac4c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9413771033287048,
"min": 0.9413771033287048,
"max": 2.87105393409729,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9019.333984375,
"min": 9019.333984375,
"max": 29497.20703125,
"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": 12.97729206085205,
"min": 0.4120900630950928,
"max": 12.97729206085205,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2530.572021484375,
"min": 79.94547271728516,
"max": 2635.604736328125,
"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": 0.06889877595805206,
"min": 0.0667230952257181,
"max": 0.07330554176815877,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27559510383220825,
"min": 0.2668923809028724,
"max": 0.36514054209407076,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1990339971494441,
"min": 0.14965298773912605,
"max": 0.29186276543666334,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7961359885977763,
"min": 0.5986119509565042,
"max": 1.362340083601428,
"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": 25.5,
"min": 4.0227272727272725,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 177.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 4.0227272727272725,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 177.0,
"max": 1413.0,
"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": "1732076878",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732077527"
},
"total": 648.993594843,
"count": 1,
"self": 0.6941235470000038,
"children": {
"run_training.setup": {
"total": 0.08766387000002851,
"count": 1,
"self": 0.08766387000002851
},
"TrainerController.start_learning": {
"total": 648.211807426,
"count": 1,
"self": 0.926544635010373,
"children": {
"TrainerController._reset_env": {
"total": 7.8338887280000336,
"count": 1,
"self": 7.8338887280000336
},
"TrainerController.advance": {
"total": 639.3635084479895,
"count": 18204,
"self": 0.4571237239895254,
"children": {
"env_step": {
"total": 638.906384724,
"count": 18204,
"self": 490.16619444699234,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.31121203999635,
"count": 18204,
"self": 2.702545543004362,
"children": {
"TorchPolicy.evaluate": {
"total": 145.608666496992,
"count": 18204,
"self": 145.608666496992
}
}
},
"workers": {
"total": 0.4289782370112789,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 646.1916481979829,
"count": 18204,
"is_parallel": true,
"self": 321.40490627098234,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003350628000021061,
"count": 1,
"is_parallel": true,
"self": 0.0010819259997560948,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002268702000264966,
"count": 10,
"is_parallel": true,
"self": 0.002268702000264966
}
}
},
"UnityEnvironment.step": {
"total": 0.05213906500000576,
"count": 1,
"is_parallel": true,
"self": 0.0010043010000799768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0059437659999730386,
"count": 1,
"is_parallel": true,
"self": 0.0059437659999730386
},
"communicator.exchange": {
"total": 0.042289850999964074,
"count": 1,
"is_parallel": true,
"self": 0.042289850999964074
},
"steps_from_proto": {
"total": 0.0029011469999886685,
"count": 1,
"is_parallel": true,
"self": 0.000493985999924007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024071610000646615,
"count": 10,
"is_parallel": true,
"self": 0.0024071610000646615
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 324.78674192700055,
"count": 18203,
"is_parallel": true,
"self": 15.341324768985146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.745609686998932,
"count": 18203,
"is_parallel": true,
"self": 7.745609686998932
},
"communicator.exchange": {
"total": 256.1964122880073,
"count": 18203,
"is_parallel": true,
"self": 256.1964122880073
},
"steps_from_proto": {
"total": 45.50339518300916,
"count": 18203,
"is_parallel": true,
"self": 9.063785966958108,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.43960921605105,
"count": 182030,
"is_parallel": true,
"self": 36.43960921605105
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017412300007890735,
"count": 1,
"self": 0.00017412300007890735,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 632.7245649488992,
"count": 676008,
"is_parallel": true,
"self": 17.96609357587306,
"children": {
"process_trajectory": {
"total": 329.679788901027,
"count": 676008,
"is_parallel": true,
"self": 328.6864187040271,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9933701969998765,
"count": 4,
"is_parallel": true,
"self": 0.9933701969998765
}
}
},
"_update_policy": {
"total": 285.0786824719992,
"count": 90,
"is_parallel": true,
"self": 77.84952221499964,
"children": {
"TorchPPOOptimizer.update": {
"total": 207.22916025699953,
"count": 4587,
"is_parallel": true,
"self": 207.22916025699953
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08769149199997628,
"count": 1,
"self": 0.0012261959998340899,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08646529600014219,
"count": 1,
"self": 0.08646529600014219
}
}
}
}
}
}
}