Subjective Reinforcement Learning for Open Complex Environments

Zhile Yang*, Haichuan Gao*, Xin Su, Shangqi Guo, Feng Chen

Abstract: Solving tasks in open environments has been one of the long-time pursuits of reinforcement learning researches. We propose that data confusion is the core underlying problem. Although there exist methods that implicitly alleviate it from different perspectives, we argue that their solutions are based on task-specific prior knowledge that is constrained to certain kinds of tasks and lacks theoretical guarantees. In this paper, Subjective Reinforcement Learning Framework is proposed to state the problem from a broader and systematic view, and subjective policy is proposed to represent existing related algorithms in general. Theoretical analysis is given about the conditions for the superiority of a subjective policy, and the relationship between model complexity and the overall performance. Results are further applied as guidance for algorithm designing without task-specific prior knowledge about tasks.

Keywords: reinforcement learning theory, subjective learning