ppo-snowball / run_logs /timers.json
stinoco's picture
First try snowball
52bd21d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9025452136993408,
"min": 0.9025452136993408,
"max": 2.8634238243103027,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8617.501953125,
"min": 8617.501953125,
"max": 29324.32421875,
"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": 12.705842018127441,
"min": 0.3917936384677887,
"max": 12.705842018127441,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2477.63916015625,
"min": 76.00796508789062,
"max": 2571.81494140625,
"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": 0.06173613250390261,
"min": 0.06173613250390261,
"max": 0.07385947124646776,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24694453001561045,
"min": 0.24694453001561045,
"max": 0.3692973562323388,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21055570003740928,
"min": 0.12390385789102783,
"max": 0.28363190094629925,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8422228001496371,
"min": 0.4956154315641113,
"max": 1.3479237217529147,
"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": 25.295454545454547,
"min": 3.3181818181818183,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 146.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.3181818181818183,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 146.0,
"max": 1379.0,
"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": "1676907505",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676907978"
},
"total": 473.7822946069999,
"count": 1,
"self": 0.44021979299998293,
"children": {
"run_training.setup": {
"total": 0.11587077599995155,
"count": 1,
"self": 0.11587077599995155
},
"TrainerController.start_learning": {
"total": 473.226204038,
"count": 1,
"self": 0.5336298739879339,
"children": {
"TrainerController._reset_env": {
"total": 9.244139789999963,
"count": 1,
"self": 9.244139789999963
},
"TrainerController.advance": {
"total": 463.3165397710118,
"count": 18203,
"self": 0.27431693300150073,
"children": {
"env_step": {
"total": 463.0422228380103,
"count": 18203,
"self": 322.0234528510058,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.751583643995,
"count": 18203,
"self": 1.462197880996996,
"children": {
"TorchPolicy.evaluate": {
"total": 139.289385762998,
"count": 18203,
"self": 30.8267695440004,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.4626162189976,
"count": 18203,
"self": 108.4626162189976
}
}
}
}
},
"workers": {
"total": 0.2671863430094845,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.7851760040011,
"count": 18203,
"is_parallel": true,
"self": 232.6748512620187,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007808920000002217,
"count": 1,
"is_parallel": true,
"self": 0.003979250999918804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0038296690000834133,
"count": 10,
"is_parallel": true,
"self": 0.0038296690000834133
}
}
},
"UnityEnvironment.step": {
"total": 0.03425506600001427,
"count": 1,
"is_parallel": true,
"self": 0.0005566020000742355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000366734999943219,
"count": 1,
"is_parallel": true,
"self": 0.000366734999943219
},
"communicator.exchange": {
"total": 0.03151460499998393,
"count": 1,
"is_parallel": true,
"self": 0.03151460499998393
},
"steps_from_proto": {
"total": 0.0018171240000128819,
"count": 1,
"is_parallel": true,
"self": 0.00041839200014237576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013987319998705061,
"count": 10,
"is_parallel": true,
"self": 0.0013987319998705061
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.11032474198237,
"count": 18202,
"is_parallel": true,
"self": 9.656117954993078,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.120775829005652,
"count": 18202,
"is_parallel": true,
"self": 5.120775829005652
},
"communicator.exchange": {
"total": 192.80923928899324,
"count": 18202,
"is_parallel": true,
"self": 192.80923928899324
},
"steps_from_proto": {
"total": 31.524191668990397,
"count": 18202,
"is_parallel": true,
"self": 6.804670809965501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.719520859024897,
"count": 182020,
"is_parallel": true,
"self": 24.719520859024897
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011254100013502466,
"count": 1,
"self": 0.00011254100013502466,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.8129887298967,
"count": 407992,
"is_parallel": true,
"self": 10.310999640903447,
"children": {
"process_trajectory": {
"total": 261.1785457019936,
"count": 407992,
"is_parallel": true,
"self": 260.21156600699385,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9669796949997362,
"count": 4,
"is_parallel": true,
"self": 0.9669796949997362
}
}
},
"_update_policy": {
"total": 188.32344338699966,
"count": 90,
"is_parallel": true,
"self": 64.3758256279906,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.94761775900906,
"count": 4587,
"is_parallel": true,
"self": 123.94761775900906
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13178206200018394,
"count": 1,
"self": 0.0013052240003617044,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13047683799982224,
"count": 1,
"self": 0.13047683799982224
}
}
}
}
}
}
}