SEMI: Self-supervised Exploration via Multisensory Incongruity
Jianren Wang,Ziwen Zhuang,Hang Zhao,Jianren Wang,Ziwen Zhuang,Hang Zhao
Efficient exploration is a long-standing problem in reinforcement learning since extrinsic rewards are usually sparse or missing. A popular solution to this issue is to feed an agent with novelty signals as intrinsic rewards. In this work, we introduce SEMI, a self-supervised exploration policy by incentivizing the agent to maximize a new novelty signal: multisensory incongruity, which can be meas...
