bakermann's picture
First Push
225ef7f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.876045823097229,
"min": 0.8717317581176758,
"max": 2.873237371444702,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8374.1220703125,
"min": 8374.1220703125,
"max": 29456.4296875,
"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": 13.092761039733887,
"min": 0.2181505560874939,
"max": 13.092761039733887,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2553.08837890625,
"min": 42.32120895385742,
"max": 2640.909423828125,
"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": 0.06905512828505415,
"min": 0.0597248368179345,
"max": 0.07329961483072325,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2762205131402166,
"min": 0.238899347271738,
"max": 0.3660506633961774,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19104886398303744,
"min": 0.13044067660310105,
"max": 0.30763208211637016,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7641954559321498,
"min": 0.5217627064124042,
"max": 1.5381604105818507,
"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": 25.886363636363637,
"min": 3.4318181818181817,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1139.0,
"min": 151.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.886363636363637,
"min": 3.4318181818181817,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1139.0,
"min": 151.0,
"max": 1408.0,
"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": "1721160958",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721161419"
},
"total": 461.2460009989991,
"count": 1,
"self": 0.4248799329980102,
"children": {
"run_training.setup": {
"total": 0.05213428100068995,
"count": 1,
"self": 0.05213428100068995
},
"TrainerController.start_learning": {
"total": 460.7689867850004,
"count": 1,
"self": 0.5553393159862026,
"children": {
"TrainerController._reset_env": {
"total": 2.374879963999774,
"count": 1,
"self": 2.374879963999774
},
"TrainerController.advance": {
"total": 457.7483585570153,
"count": 18202,
"self": 0.2657256029342534,
"children": {
"env_step": {
"total": 457.48263295408105,
"count": 18202,
"self": 296.8856869931351,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.31659560207117,
"count": 18202,
"self": 1.4803183901512966,
"children": {
"TorchPolicy.evaluate": {
"total": 158.83627721191988,
"count": 18202,
"self": 158.83627721191988
}
}
},
"workers": {
"total": 0.28035035887478443,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.5453003437997,
"count": 18202,
"is_parallel": true,
"self": 233.79347251281433,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024364129985769978,
"count": 1,
"is_parallel": true,
"self": 0.0007266079992405139,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017098049993364839,
"count": 10,
"is_parallel": true,
"self": 0.0017098049993364839
}
}
},
"UnityEnvironment.step": {
"total": 0.06377144399993995,
"count": 1,
"is_parallel": true,
"self": 0.0006506799982162192,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038726700040569995,
"count": 1,
"is_parallel": true,
"self": 0.00038726700040569995
},
"communicator.exchange": {
"total": 0.060746804001610144,
"count": 1,
"is_parallel": true,
"self": 0.060746804001610144
},
"steps_from_proto": {
"total": 0.001986692999707884,
"count": 1,
"is_parallel": true,
"self": 0.0003765620003832737,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016101309993246105,
"count": 10,
"is_parallel": true,
"self": 0.0016101309993246105
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.75182783098535,
"count": 18201,
"is_parallel": true,
"self": 10.117698377905981,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.408851218975542,
"count": 18201,
"is_parallel": true,
"self": 5.408851218975542
},
"communicator.exchange": {
"total": 176.10013642205922,
"count": 18201,
"is_parallel": true,
"self": 176.10013642205922
},
"steps_from_proto": {
"total": 34.1251418120446,
"count": 18201,
"is_parallel": true,
"self": 6.455231306985297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.669910505059306,
"count": 182010,
"is_parallel": true,
"self": 27.669910505059306
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000122112998724333,
"count": 1,
"self": 0.000122112998724333,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.01980372137405,
"count": 679662,
"is_parallel": true,
"self": 14.522516027869642,
"children": {
"process_trajectory": {
"total": 250.14481538950713,
"count": 679662,
"is_parallel": true,
"self": 249.53572134050773,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6090940489993955,
"count": 4,
"is_parallel": true,
"self": 0.6090940489993955
}
}
},
"_update_policy": {
"total": 187.35247230399727,
"count": 90,
"is_parallel": true,
"self": 59.77666507702088,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.5758072269764,
"count": 4587,
"is_parallel": true,
"self": 127.5758072269764
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09028683500037005,
"count": 1,
"self": 0.0009635460010031238,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08932328899936692,
"count": 1,
"self": 0.08932328899936692
}
}
}
}
}
}
}