gmalivenko's picture
ml-agents test
ba7dae3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8782681226730347,
"min": 0.874020516872406,
"max": 2.858748197555542,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8385.7041015625,
"min": 8385.7041015625,
"max": 29276.44140625,
"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": 12.85213851928711,
"min": 0.3618074059486389,
"max": 12.85213851928711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2506.1669921875,
"min": 70.19063568115234,
"max": 2591.8017578125,
"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": 0.06780244014111768,
"min": 0.06209790115153381,
"max": 0.0761669096777469,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2712097605644707,
"min": 0.26216795454035724,
"max": 0.38083454838873454,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19740257609416456,
"min": 0.13032905892217897,
"max": 0.28054167862031976,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7896103043766582,
"min": 0.5213162356887159,
"max": 1.4027083931015987,
"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": 25.34090909090909,
"min": 3.727272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 164.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.727272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 164.0,
"max": 1400.0,
"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": "1777798139",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/user/miniforge3/envs/py31012/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1777798353"
},
"total": 213.97156116599945,
"count": 1,
"self": 0.32222544999967795,
"children": {
"run_training.setup": {
"total": 0.014287011999840615,
"count": 1,
"self": 0.014287011999840615
},
"TrainerController.start_learning": {
"total": 213.63504870399993,
"count": 1,
"self": 0.40176526678260416,
"children": {
"TrainerController._reset_env": {
"total": 1.2746128350008803,
"count": 1,
"self": 1.2746128350008803
},
"TrainerController.advance": {
"total": 211.91975825421832,
"count": 18201,
"self": 0.23230347882781643,
"children": {
"env_step": {
"total": 211.6874547753905,
"count": 18201,
"self": 156.61243310679492,
"children": {
"SubprocessEnvManager._take_step": {
"total": 54.84178998784046,
"count": 18201,
"self": 0.8168245817942079,
"children": {
"TorchPolicy.evaluate": {
"total": 54.02496540604625,
"count": 18201,
"self": 54.02496540604625
}
}
},
"workers": {
"total": 0.23323168075512513,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 213.19528417213223,
"count": 18201,
"is_parallel": true,
"self": 98.87507307280976,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00410834300055285,
"count": 1,
"is_parallel": true,
"self": 0.0006893330028105993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0034190099977422506,
"count": 10,
"is_parallel": true,
"self": 0.0034190099977422506
}
}
},
"UnityEnvironment.step": {
"total": 0.02330345100199338,
"count": 1,
"is_parallel": true,
"self": 0.00020840600336669013,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020994299848098308,
"count": 1,
"is_parallel": true,
"self": 0.00020994299848098308
},
"communicator.exchange": {
"total": 0.022195000001374865,
"count": 1,
"is_parallel": true,
"self": 0.022195000001374865
},
"steps_from_proto": {
"total": 0.0006901019987708423,
"count": 1,
"is_parallel": true,
"self": 0.0001563749938213732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005337270049494691,
"count": 10,
"is_parallel": true,
"self": 0.0005337270049494691
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 114.32021109932248,
"count": 18200,
"is_parallel": true,
"self": 4.483406874260254,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.6889497519478027,
"count": 18200,
"is_parallel": true,
"self": 2.6889497519478027
},
"communicator.exchange": {
"total": 93.52134230207594,
"count": 18200,
"is_parallel": true,
"self": 93.52134230207594
},
"steps_from_proto": {
"total": 13.626512171038485,
"count": 18200,
"is_parallel": true,
"self": 3.0513702646458114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10.575141906392673,
"count": 182000,
"is_parallel": true,
"self": 10.575141906392673
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.0031998903723434e-05,
"count": 1,
"self": 3.0031998903723434e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 210.78255124853604,
"count": 284564,
"is_parallel": true,
"self": 3.357171095936792,
"children": {
"process_trajectory": {
"total": 109.7414910825828,
"count": 284564,
"is_parallel": true,
"self": 109.47730296558075,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2641881170020497,
"count": 4,
"is_parallel": true,
"self": 0.2641881170020497
}
}
},
"_update_policy": {
"total": 97.68388907001645,
"count": 90,
"is_parallel": true,
"self": 22.24528066203129,
"children": {
"TorchPPOOptimizer.update": {
"total": 75.43860840798516,
"count": 4587,
"is_parallel": true,
"self": 75.43860840798516
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0388823159992171,
"count": 1,
"self": 0.0004064069980813656,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03847590900113573,
"count": 1,
"self": 0.03847590900113573
}
}
}
}
}
}
}