hanslab37's picture
First Push
a04be2e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7929317355155945,
"min": 0.7781063318252563,
"max": 2.847013235092163,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7536.0234375,
"min": 7536.0234375,
"max": 29062.310546875,
"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": 12.757514953613281,
"min": 0.3581220805644989,
"max": 12.757514953613281,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2487.71533203125,
"min": 69.4756851196289,
"max": 2590.30029296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06550799752614123,
"min": 0.06506212833335574,
"max": 0.07386901554441555,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2620319901045649,
"min": 0.26024851333342297,
"max": 0.35914879788270254,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19688631192434067,
"min": 0.12767643495645448,
"max": 0.2973218695205801,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7875452476973627,
"min": 0.5107057398258179,
"max": 1.4866093476029005,
"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.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.Environment.CumulativeReward.mean": {
"value": 24.772727272727273,
"min": 3.3863636363636362,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 149.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 3.3863636363636362,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 149.0,
"max": 1396.0,
"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": "1750404973",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/root/miniconda3/envs/stable-base/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./trained-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": "2.7.1+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1750405506"
},
"total": 518.7503968739766,
"count": 1,
"self": 0.3261248199851252,
"children": {
"run_training.setup": {
"total": 0.11076671601040289,
"count": 1,
"self": 0.11076671601040289
},
"TrainerController.start_learning": {
"total": 518.313505337981,
"count": 1,
"self": 0.36339177636546083,
"children": {
"TrainerController._reset_env": {
"total": 10.168291451991536,
"count": 1,
"self": 10.168291451991536
},
"TrainerController.advance": {
"total": 507.69088441162603,
"count": 18192,
"self": 0.3399742757610511,
"children": {
"env_step": {
"total": 362.2896798142756,
"count": 18192,
"self": 244.0553100920224,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.02504452853464,
"count": 18192,
"self": 1.2576848848257214,
"children": {
"TorchPolicy.evaluate": {
"total": 116.76735964370891,
"count": 18192,
"self": 116.76735964370891
}
}
},
"workers": {
"total": 0.2093251937185414,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 517.3959917994216,
"count": 18192,
"is_parallel": true,
"self": 295.6620696738537,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.028859622980235144,
"count": 1,
"is_parallel": true,
"self": 0.027561210008570924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00129841297166422,
"count": 10,
"is_parallel": true,
"self": 0.00129841297166422
}
}
},
"UnityEnvironment.step": {
"total": 0.02425116000813432,
"count": 1,
"is_parallel": true,
"self": 0.0003251690068282187,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015738597721792758,
"count": 1,
"is_parallel": true,
"self": 0.00015738597721792758
},
"communicator.exchange": {
"total": 0.022585657017771155,
"count": 1,
"is_parallel": true,
"self": 0.022585657017771155
},
"steps_from_proto": {
"total": 0.0011829480063170195,
"count": 1,
"is_parallel": true,
"self": 0.00027934799436479807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009036000119522214,
"count": 10,
"is_parallel": true,
"self": 0.0009036000119522214
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.73392212556791,
"count": 18191,
"is_parallel": true,
"self": 4.135973476979416,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.733247428899631,
"count": 18191,
"is_parallel": true,
"self": 2.733247428899631
},
"communicator.exchange": {
"total": 200.2527282886731,
"count": 18191,
"is_parallel": true,
"self": 200.2527282886731
},
"steps_from_proto": {
"total": 14.61197293101577,
"count": 18191,
"is_parallel": true,
"self": 3.5177898864785675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.094183044537203,
"count": 181910,
"is_parallel": true,
"self": 11.094183044537203
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 145.0612303215894,
"count": 18192,
"self": 0.48023046433809213,
"children": {
"process_trajectory": {
"total": 32.625724405254005,
"count": 18192,
"self": 31.851501397264656,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7742230079893488,
"count": 4,
"self": 0.7742230079893488
}
}
},
"_update_policy": {
"total": 111.9552754519973,
"count": 90,
"self": 24.04738772532437,
"children": {
"TorchPPOOptimizer.update": {
"total": 87.90788772667293,
"count": 4587,
"self": 87.90788772667293
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.3329997677356005e-06,
"count": 1,
"self": 3.3329997677356005e-06
},
"TrainerController._save_models": {
"total": 0.09093436499824747,
"count": 1,
"self": 0.0009633359732106328,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08997102902503684,
"count": 1,
"self": 0.08997102902503684
}
}
}
}
}
}
}