Low Dimensional State Representation Learning With Reward-Shaped Priors

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2020)

引用 3|浏览31
暂无评分
摘要
Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations, often requires processing and storage of a huge amount of data. In the context of robotics, the cost of data from real robotics hardware is usually very high, thus solutions that achieve high sample-efficiency are needed. We propose a method that aims at learning a mapping from the observations into a lower-dimensional state space. This mapping is learned with unsupervised learning using loss functions shaped to incorporate prior knowledge of the environment and the task. Using the samples from the state space, the optimal policy is quickly and efficiently learned. We test the method on several mobile robot navigation tasks in a simulation environment and also on a real robot. A video of our experiments can be found at: https://youtu.beidgWxmfSv95U
更多
查看译文
关键词
Reinforcement Learning, State Representation Learning, Robotics
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要