Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning☆.

Sample efficiency, which refers to the number of samples required for a learning agent to attain a specific level of performance, is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks can significantly improve sample efficiency. Recent research indicates that successor feature (SF) RL algorithms enable knowledge generalization between tasks with different rewards but identical transition dynamics. It has recently been hypothesized that combining model-based (MB) methods with SF algorithms can alleviate the limitation of fixed transition dynamics. Furthermore, uncertainty-aware exploration is widely recognized as another appealing approach for improving sample efficiency. An agent can efficiently explore to better understand an environment by tracking uncertainty about the value of each available action. Putting together two ideas of hybrid model-based successor feature (MB-SF) and uncertainty leads to an approach to the problem of sample efficient uncertainty-aware knowledge transfer across tasks with different transition dynamics or/and reward functions. In this paper, the uncertainty of the value of each action is approximated by a Kalman filter (KF)-based multiple-model adaptive estimation. This KF-based framework treats the parameters of a model as random variables. To the best of our knowledge, this is the first attempt at formulating a hybrid MB-SF algorithm capable of generalizing knowledge across large or continuous state space tasks with various transition dynamics while requiring less computation at decision time than MB methods. We highlight why previous SF-based methods are constrained to knowledge generalization across same transition dynamics, present our novel approach on a firm theoretical foundation, and design a set of demonstration tasks to empirically validate the effectiveness of our proposed approach. The number of samples required to learn the tasks was compared to recent SF and MB baselines. The results show that our algorithm generalizes its knowledge across different transition dynamics, learns downstream tasks with significantly fewer samples than starting from scratch, and outperforms existing approaches. We believe that our proposed framework can account for the computationally efficient behavioural flexibilities observed in the empirical literature and can also serve as a solid theoretical foundation for future experimental work.