Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

IEEE International Conference on Robotics and Automation(2022)

引用 27|浏览0
暂无评分
摘要
World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how such agents generalize to real-world autonomous vehicle control tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the choice of their observation model. We provide extensive empirical evidence for the effectiveness of world models provided with long enough memory horizons in sim2real tasks.
更多
查看译文
关键词
model-free agents,model-based agents,autonomous racing,latent imagination space,deep reinforcement learning algorithms,real-world robotics applications,real-world autonomous vehicle control tasks,time-lap tasks,F1TENTH racing robot,high-dimensional LiDAR sensor,continuous-control setting,zero-shot transfer
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