ppo-snowb / run_logs /timers.json
aeyae's picture
1
e85313d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9464503526687622,
"min": 0.9413878321647644,
"max": 2.843414545059204,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9047.119140625,
"min": 9047.119140625,
"max": 29275.796875,
"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": 12.978432655334473,
"min": 0.3470582067966461,
"max": 12.978432655334473,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2530.79443359375,
"min": 67.32929229736328,
"max": 2628.189453125,
"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": 0.07020682886678853,
"min": 0.0640544143011628,
"max": 0.07536557302934371,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2808273154671541,
"min": 0.2562176572046512,
"max": 0.37241751377758403,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1977694230336769,
"min": 0.10748118939056225,
"max": 0.2769577009420769,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7910776921347076,
"min": 0.429924757562249,
"max": 1.3847885047103845,
"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": 25.613636363636363,
"min": 3.227272727272727,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 142.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.227272727272727,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 142.0,
"max": 1386.0,
"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": "1708364353",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708364806"
},
"total": 452.69015828400006,
"count": 1,
"self": 0.4381865130000051,
"children": {
"run_training.setup": {
"total": 0.050239526000041224,
"count": 1,
"self": 0.050239526000041224
},
"TrainerController.start_learning": {
"total": 452.201732245,
"count": 1,
"self": 0.5846119750202661,
"children": {
"TrainerController._reset_env": {
"total": 3.3982462539999005,
"count": 1,
"self": 3.3982462539999005
},
"TrainerController.advance": {
"total": 448.1219151509798,
"count": 18200,
"self": 0.2855379889889491,
"children": {
"env_step": {
"total": 447.83637716199087,
"count": 18200,
"self": 289.5755450520494,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.95956515298258,
"count": 18200,
"self": 1.5148081949801053,
"children": {
"TorchPolicy.evaluate": {
"total": 156.44475695800247,
"count": 18200,
"self": 156.44475695800247
}
}
},
"workers": {
"total": 0.30126695695889794,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 451.0528442260048,
"count": 18200,
"is_parallel": true,
"self": 223.42649446801852,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00631058600004053,
"count": 1,
"is_parallel": true,
"self": 0.004267945000037798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020426410000027317,
"count": 10,
"is_parallel": true,
"self": 0.0020426410000027317
}
}
},
"UnityEnvironment.step": {
"total": 0.03796507800007021,
"count": 1,
"is_parallel": true,
"self": 0.0005982600000606908,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041942400002881186,
"count": 1,
"is_parallel": true,
"self": 0.00041942400002881186
},
"communicator.exchange": {
"total": 0.03487543699998241,
"count": 1,
"is_parallel": true,
"self": 0.03487543699998241
},
"steps_from_proto": {
"total": 0.0020719569999982923,
"count": 1,
"is_parallel": true,
"self": 0.0004283849999637823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00164357200003451,
"count": 10,
"is_parallel": true,
"self": 0.00164357200003451
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.6263497579863,
"count": 18199,
"is_parallel": true,
"self": 10.778325761988413,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.567406314992354,
"count": 18199,
"is_parallel": true,
"self": 5.567406314992354
},
"communicator.exchange": {
"total": 175.6503694210047,
"count": 18199,
"is_parallel": true,
"self": 175.6503694210047
},
"steps_from_proto": {
"total": 35.630248260000826,
"count": 18199,
"is_parallel": true,
"self": 6.54678958500665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.083458674994176,
"count": 181990,
"is_parallel": true,
"self": 29.083458674994176
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.0433000094708405e-05,
"count": 1,
"self": 4.0433000094708405e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 441.9655888459183,
"count": 681634,
"is_parallel": true,
"self": 14.890459684060602,
"children": {
"process_trajectory": {
"total": 243.91607496185804,
"count": 681634,
"is_parallel": true,
"self": 243.40877778885817,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5072971729998699,
"count": 4,
"is_parallel": true,
"self": 0.5072971729998699
}
}
},
"_update_policy": {
"total": 183.15905419999967,
"count": 90,
"is_parallel": true,
"self": 51.77566340299029,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.38339079700938,
"count": 4587,
"is_parallel": true,
"self": 131.38339079700938
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09691843199993855,
"count": 1,
"self": 0.0012307849999615428,
"children": {
"RLTrainer._checkpoint": {
"total": 0.095687646999977,
"count": 1,
"self": 0.095687646999977
}
}
}
}
}
}
}