ankarb's picture
First Push
09d036f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9422601461410522,
"min": 0.9422601461410522,
"max": 2.8634300231933594,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9007.064453125,
"min": 9007.064453125,
"max": 29324.38671875,
"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": 13.262930870056152,
"min": 0.3991468846797943,
"max": 13.262930870056152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2586.271484375,
"min": 77.43449401855469,
"max": 2681.8701171875,
"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": 0.06838352883428075,
"min": 0.0624649984574895,
"max": 0.0730400789734524,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.273534115337123,
"min": 0.25895315930178825,
"max": 0.36520039486726197,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17546589172207844,
"min": 0.14767347549330262,
"max": 0.28787401178303884,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7018635668883138,
"min": 0.5906939019732105,
"max": 1.439370058915194,
"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": 26.431818181818183,
"min": 4.181818181818182,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1163.0,
"min": 184.0,
"max": 1431.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.431818181818183,
"min": 4.181818181818182,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1163.0,
"min": 184.0,
"max": 1431.0,
"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": "1705513186",
"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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705513644"
},
"total": 458.0406131779996,
"count": 1,
"self": 0.5445233789996564,
"children": {
"run_training.setup": {
"total": 0.06648270000005141,
"count": 1,
"self": 0.06648270000005141
},
"TrainerController.start_learning": {
"total": 457.4296070989999,
"count": 1,
"self": 0.5516303650206282,
"children": {
"TrainerController._reset_env": {
"total": 2.729181907000111,
"count": 1,
"self": 2.729181907000111
},
"TrainerController.advance": {
"total": 453.9522275289796,
"count": 18201,
"self": 0.25352688998054873,
"children": {
"env_step": {
"total": 453.69870063899907,
"count": 18201,
"self": 303.24586714901625,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.1770891309534,
"count": 18201,
"self": 1.4171219149307035,
"children": {
"TorchPolicy.evaluate": {
"total": 148.7599672160227,
"count": 18201,
"self": 148.7599672160227
}
}
},
"workers": {
"total": 0.2757443590294315,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.05008729498377,
"count": 18201,
"is_parallel": true,
"self": 231.1995774479301,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027739490001295053,
"count": 1,
"is_parallel": true,
"self": 0.000629776000550919,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021441729995785863,
"count": 10,
"is_parallel": true,
"self": 0.0021441729995785863
}
}
},
"UnityEnvironment.step": {
"total": 0.0815327319996868,
"count": 1,
"is_parallel": true,
"self": 0.000618415000189998,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003880799999933515,
"count": 1,
"is_parallel": true,
"self": 0.0003880799999933515
},
"communicator.exchange": {
"total": 0.07861340899989955,
"count": 1,
"is_parallel": true,
"self": 0.07861340899989955
},
"steps_from_proto": {
"total": 0.0019128279996039055,
"count": 1,
"is_parallel": true,
"self": 0.00037797300046804594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015348549991358595,
"count": 10,
"is_parallel": true,
"self": 0.0015348549991358595
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.85050984705367,
"count": 18200,
"is_parallel": true,
"self": 10.50131188809246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.183590120004283,
"count": 18200,
"is_parallel": true,
"self": 5.183590120004283
},
"communicator.exchange": {
"total": 176.57531122197543,
"count": 18200,
"is_parallel": true,
"self": 176.57531122197543
},
"steps_from_proto": {
"total": 32.590296616981504,
"count": 18200,
"is_parallel": true,
"self": 6.033369108068655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.55692750891285,
"count": 182000,
"is_parallel": true,
"self": 26.55692750891285
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012829899969801772,
"count": 1,
"self": 0.00012829899969801772,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 448.5587441228022,
"count": 677280,
"is_parallel": true,
"self": 13.697264239953256,
"children": {
"process_trajectory": {
"total": 244.9925615048478,
"count": 677280,
"is_parallel": true,
"self": 243.62195273684756,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3706087680002383,
"count": 4,
"is_parallel": true,
"self": 1.3706087680002383
}
}
},
"_update_policy": {
"total": 189.86891837800113,
"count": 90,
"is_parallel": true,
"self": 64.15958195599842,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.7093364220027,
"count": 4587,
"is_parallel": true,
"self": 125.7093364220027
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.19643899899983808,
"count": 1,
"self": 0.004662168999857386,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1917768299999807,
"count": 1,
"self": 0.1917768299999807
}
}
}
}
}
}
}