grib0ed0v's picture
First Push
ec3af91 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9894164800643921,
"min": 0.9894164800643921,
"max": 2.878127336502075,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9468.7158203125,
"min": 9468.7158203125,
"max": 29506.560546875,
"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": 12.841008186340332,
"min": 0.1894523948431015,
"max": 12.841008186340332,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2503.99658203125,
"min": 36.75376510620117,
"max": 2592.4306640625,
"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": 0.06833439740266305,
"min": 0.06143617244416223,
"max": 0.07874002631305142,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2733375896106522,
"min": 0.2598330769318921,
"max": 0.34965148616659764,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2143885636446523,
"min": 0.1283490205475805,
"max": 0.29705295061656073,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8575542545786092,
"min": 0.513396082190322,
"max": 1.4338704593041365,
"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": 3.25,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 143.0,
"max": 1372.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.25,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 143.0,
"max": 1372.0,
"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": "1727775756",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727776357"
},
"total": 600.638968296,
"count": 1,
"self": 1.1602773580000303,
"children": {
"run_training.setup": {
"total": 0.0955621129999713,
"count": 1,
"self": 0.0955621129999713
},
"TrainerController.start_learning": {
"total": 599.3831288250001,
"count": 1,
"self": 0.8457900169995582,
"children": {
"TrainerController._reset_env": {
"total": 2.978613614999972,
"count": 1,
"self": 2.978613614999972
},
"TrainerController.advance": {
"total": 595.4245993070006,
"count": 18207,
"self": 0.4084174600021697,
"children": {
"env_step": {
"total": 595.0161818469984,
"count": 18207,
"self": 460.9644302409989,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.63992392300094,
"count": 18207,
"self": 2.3878720169992675,
"children": {
"TorchPolicy.evaluate": {
"total": 131.25205190600167,
"count": 18207,
"self": 131.25205190600167
}
}
},
"workers": {
"total": 0.4118276829985348,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 597.5011514289939,
"count": 18207,
"is_parallel": true,
"self": 281.8384344229933,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0036487560000182384,
"count": 1,
"is_parallel": true,
"self": 0.0009281119999400289,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027206440000782095,
"count": 10,
"is_parallel": true,
"self": 0.0027206440000782095
}
}
},
"UnityEnvironment.step": {
"total": 0.04631363400000055,
"count": 1,
"is_parallel": true,
"self": 0.0008757740000078229,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004463829999963309,
"count": 1,
"is_parallel": true,
"self": 0.0004463829999963309
},
"communicator.exchange": {
"total": 0.04257447200001252,
"count": 1,
"is_parallel": true,
"self": 0.04257447200001252
},
"steps_from_proto": {
"total": 0.002417004999983874,
"count": 1,
"is_parallel": true,
"self": 0.0005200619999641276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018969430000197463,
"count": 10,
"is_parallel": true,
"self": 0.0018969430000197463
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 315.6627170060006,
"count": 18206,
"is_parallel": true,
"self": 15.048824851990389,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.79280458900439,
"count": 18206,
"is_parallel": true,
"self": 7.79280458900439
},
"communicator.exchange": {
"total": 248.54467149600146,
"count": 18206,
"is_parallel": true,
"self": 248.54467149600146
},
"steps_from_proto": {
"total": 44.27641606900437,
"count": 18206,
"is_parallel": true,
"self": 8.867536522995294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.408879546009075,
"count": 182060,
"is_parallel": true,
"self": 35.408879546009075
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018713999997999053,
"count": 1,
"self": 0.00018713999997999053,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 588.8898451790103,
"count": 744268,
"is_parallel": true,
"self": 16.92927942704364,
"children": {
"process_trajectory": {
"total": 314.91838970196625,
"count": 744268,
"is_parallel": true,
"self": 313.99823834496624,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9201513570000088,
"count": 4,
"is_parallel": true,
"self": 0.9201513570000088
}
}
},
"_update_policy": {
"total": 257.0421760500005,
"count": 90,
"is_parallel": true,
"self": 71.92908927000178,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.1130867799987,
"count": 4587,
"is_parallel": true,
"self": 185.1130867799987
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13393874600001254,
"count": 1,
"self": 0.0024438819999659245,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13149486400004662,
"count": 1,
"self": 0.13149486400004662
}
}
}
}
}
}
}