pkalkman's picture
First Push
ea9ccb0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8484742045402527,
"min": 0.84836345911026,
"max": 2.8705708980560303,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8119.89794921875,
"min": 8119.89794921875,
"max": 29397.517578125,
"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": 12.795982360839844,
"min": 0.4802817106246948,
"max": 12.795982360839844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2495.216552734375,
"min": 93.17465209960938,
"max": 2606.968017578125,
"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": 0.06804920880462947,
"min": 0.061624763971171795,
"max": 0.07393070763546526,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2721968352185179,
"min": 0.24649905588468718,
"max": 0.3640533444407743,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22124377418966854,
"min": 0.1311532488553876,
"max": 0.2690391233738731,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8849750967586741,
"min": 0.5246129954215504,
"max": 1.3451956168693655,
"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": 3.5,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 154.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.5,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 154.0,
"max": 1402.0,
"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": "1729184388",
"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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729184938"
},
"total": 549.659282738,
"count": 1,
"self": 0.48038468900006137,
"children": {
"run_training.setup": {
"total": 0.08292977500002507,
"count": 1,
"self": 0.08292977500002507
},
"TrainerController.start_learning": {
"total": 549.0959682739999,
"count": 1,
"self": 0.7824780600120675,
"children": {
"TrainerController._reset_env": {
"total": 5.9155406300000095,
"count": 1,
"self": 5.9155406300000095
},
"TrainerController.advance": {
"total": 542.3162885599877,
"count": 18203,
"self": 0.38179269599027066,
"children": {
"env_step": {
"total": 541.9344958639974,
"count": 18203,
"self": 418.59845424401294,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.94021080898153,
"count": 18203,
"self": 2.0236952739851404,
"children": {
"TorchPolicy.evaluate": {
"total": 120.91651553499639,
"count": 18203,
"self": 120.91651553499639
}
}
},
"workers": {
"total": 0.39583081100295203,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 547.3806822369867,
"count": 18203,
"is_parallel": true,
"self": 254.7347478209906,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0032422510000742477,
"count": 1,
"is_parallel": true,
"self": 0.0008110230000966112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024312279999776365,
"count": 10,
"is_parallel": true,
"self": 0.0024312279999776365
}
}
},
"UnityEnvironment.step": {
"total": 0.04180845300004421,
"count": 1,
"is_parallel": true,
"self": 0.0008067550000987467,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004700949999687509,
"count": 1,
"is_parallel": true,
"self": 0.0004700949999687509
},
"communicator.exchange": {
"total": 0.03811305700003231,
"count": 1,
"is_parallel": true,
"self": 0.03811305700003231
},
"steps_from_proto": {
"total": 0.0024185459999443992,
"count": 1,
"is_parallel": true,
"self": 0.000486933999923167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019316120000212322,
"count": 10,
"is_parallel": true,
"self": 0.0019316120000212322
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 292.64593441599607,
"count": 18202,
"is_parallel": true,
"self": 14.01324467296888,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.008195173019772,
"count": 18202,
"is_parallel": true,
"self": 7.008195173019772
},
"communicator.exchange": {
"total": 229.92493314800447,
"count": 18202,
"is_parallel": true,
"self": 229.92493314800447
},
"steps_from_proto": {
"total": 41.699561422002944,
"count": 18202,
"is_parallel": true,
"self": 8.403469683012645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.2960917389903,
"count": 182020,
"is_parallel": true,
"self": 33.2960917389903
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001457260000279348,
"count": 1,
"self": 0.0001457260000279348,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 535.4956642520443,
"count": 757224,
"is_parallel": true,
"self": 16.593483464981887,
"children": {
"process_trajectory": {
"total": 290.82347707206304,
"count": 757224,
"is_parallel": true,
"self": 289.6704156810631,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1530613909999374,
"count": 4,
"is_parallel": true,
"self": 1.1530613909999374
}
}
},
"_update_policy": {
"total": 228.0787037149994,
"count": 90,
"is_parallel": true,
"self": 67.80216102299619,
"children": {
"TorchPPOOptimizer.update": {
"total": 160.2765426920032,
"count": 4587,
"is_parallel": true,
"self": 160.2765426920032
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08151529800011303,
"count": 1,
"self": 0.0011524690000896953,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08036282900002334,
"count": 1,
"self": 0.08036282900002334
}
}
}
}
}
}
}