期刊
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162
卷 -, 期 -, 页码 -出版社
JMLR-JOURNAL MACHINE LEARNING RESEARCH
关键词
-
The ability to separate signal from noise and reason with clean abstractions is crucial for intelligence. This work proposes a method of learning a Denoised MDP that categorizes and factors out certain noise distractors, leading to superior performance in various tasks.
The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence. With this ability, humans can efficiently perform real world tasks without considering all possible nuisance factors. How can artificial agents do the same? What kind of information can agents safely discard as noises? In this work, we categorize information out in the wild into four types based on controllability and relation with reward, and formulate useful information as that which is both controllable and reward-relevant. This framework clarifies the kinds information removed by various prior work on representation learning in reinforcement learning (RL), and leads to our proposed approach of learning a Denoised MDP that explicitly factors out certain noise distractors. Extensive experiments on variants of DeepMind Control Suite and RoboDesk demonstrate superior performance of our denoised world model over using raw observations alone, and over prior works, across policy optimization control tasks as well as the non-control task of joint position regression.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据