Lodeing's picture
First Push
47d4ba5
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8505288362503052,
"min": 0.8079631924629211,
"max": 2.890352964401245,
"count": 135
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8120.849609375,
"min": 7845.3330078125,
"max": 29656.125,
"count": 135
},
"SnowballTarget.Step.mean": {
"value": 1349944.0,
"min": 9952.0,
"max": 1349944.0,
"count": 135
},
"SnowballTarget.Step.sum": {
"value": 1349944.0,
"min": 9952.0,
"max": 1349944.0,
"count": 135
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 10.50064468383789,
"min": 0.1544601172208786,
"max": 10.50064468383789,
"count": 135
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2037.125,
"min": 29.965261459350586,
"max": 2141.1591796875,
"count": 135
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 135
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 135
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.40909090909091,
"min": 2.8545454545454545,
"max": 27.622222222222224,
"count": 135
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1206.0,
"min": 127.0,
"max": 1511.0,
"count": 135
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 41.11363636363637,
"min": 4.281818181818182,
"max": 41.43333333333333,
"count": 135
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1809.0,
"min": 190.5,
"max": 2266.5,
"count": 135
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.048568092357677145,
"min": 0.04315598731524968,
"max": 0.05233603015915244,
"count": 135
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09713618471535429,
"min": 0.08631197463049936,
"max": 0.15480067924562557,
"count": 135
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3307282186606351,
"min": 0.18504275109838036,
"max": 0.6004213426919545,
"count": 135
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6614564373212702,
"min": 0.37008550219676073,
"max": 1.7397729964817272,
"count": 135
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.65590144112e-06,
"min": 8.65590144112e-06,
"max": 9.99348806512e-06,
"count": 135
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.731180288224e-05,
"min": 1.731180288224e-05,
"max": 2.989466505336e-05,
"count": 135
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.18655887999999998,
"min": 0.18655887999999998,
"max": 0.19993488000000004,
"count": 135
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.37311775999999997,
"min": 0.37311775999999997,
"max": 0.5989466400000001,
"count": 135
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.004329288111999999,
"min": 0.004329288111999999,
"max": 0.004996750512000001,
"count": 135
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.008658576223999999,
"min": 0.008658576223999999,
"max": 0.014947437336,
"count": 135
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 135
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 135
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1702324542",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702328988"
},
"total": 4446.398120817,
"count": 1,
"self": 0.010002880999309127,
"children": {
"run_training.setup": {
"total": 0.05727721899995686,
"count": 1,
"self": 0.05727721899995686
},
"TrainerController.start_learning": {
"total": 4446.330840717001,
"count": 1,
"self": 5.017717671993523,
"children": {
"TrainerController._reset_env": {
"total": 3.4863041270000394,
"count": 1,
"self": 3.4863041270000394
},
"TrainerController.advance": {
"total": 4437.600561458007,
"count": 123654,
"self": 1.9637114160314013,
"children": {
"env_step": {
"total": 4435.636850041976,
"count": 123654,
"self": 3368.5173555770643,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1065.0952058319976,
"count": 123654,
"self": 9.931013712015101,
"children": {
"TorchPolicy.evaluate": {
"total": 1055.1641921199825,
"count": 123654,
"self": 1055.1641921199825
}
}
},
"workers": {
"total": 2.024288632914022,
"count": 123653,
"self": 0.0,
"children": {
"worker_root": {
"total": 4436.753644028023,
"count": 123653,
"is_parallel": true,
"self": 2822.6804114438614,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004751533999979074,
"count": 1,
"is_parallel": true,
"self": 0.0032148999999890293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015366339999900447,
"count": 10,
"is_parallel": true,
"self": 0.0015366339999900447
}
}
},
"UnityEnvironment.step": {
"total": 0.0404540500001076,
"count": 1,
"is_parallel": true,
"self": 0.0006012160001773736,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003667280000172468,
"count": 1,
"is_parallel": true,
"self": 0.0003667280000172468
},
"communicator.exchange": {
"total": 0.03741654699990704,
"count": 1,
"is_parallel": true,
"self": 0.03741654699990704
},
"steps_from_proto": {
"total": 0.0020695590000059383,
"count": 1,
"is_parallel": true,
"self": 0.00039975200036224123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001669806999643697,
"count": 10,
"is_parallel": true,
"self": 0.001669806999643697
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1614.0732325841614,
"count": 123652,
"is_parallel": true,
"self": 70.26873650409243,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 36.55596096006684,
"count": 123652,
"is_parallel": true,
"self": 36.55596096006684
},
"communicator.exchange": {
"total": 1279.1948729390422,
"count": 123652,
"is_parallel": true,
"self": 1279.1948729390422
},
"steps_from_proto": {
"total": 228.05366218096003,
"count": 123652,
"is_parallel": true,
"self": 43.48627870690109,
"children": {
"_process_rank_one_or_two_observation": {
"total": 184.56738347405894,
"count": 1236520,
"is_parallel": true,
"self": 184.56738347405894
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.4879000597575214e-05,
"count": 1,
"self": 4.4879000597575214e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 4401.016182681756,
"count": 4152879,
"is_parallel": true,
"self": 91.96696177886679,
"children": {
"process_trajectory": {
"total": 2245.2697215958874,
"count": 4152880,
"is_parallel": true,
"self": 2235.972925156889,
"children": {
"RLTrainer._checkpoint": {
"total": 9.296796438998854,
"count": 27,
"is_parallel": true,
"self": 9.296796438998854
}
}
},
"_update_policy": {
"total": 2063.779499307002,
"count": 308,
"is_parallel": true,
"self": 963.7639123689585,
"children": {
"TorchPPOOptimizer.update": {
"total": 1100.0155869380435,
"count": 52385,
"is_parallel": true,
"self": 1100.0155869380435
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22621258099934494,
"count": 1,
"self": 0.003300134999335569,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22291244600000937,
"count": 1,
"self": 0.22291244600000937
}
}
}
}
}
}
}