Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning
This work addresses a foundational issue in Bayesian reinforcement learning for researchers and practitioners, though it appears incremental as it builds on existing Bayesian approaches.
The paper tackles the problem of Bayesian reinforcement learning by introducing Inferential Induction, a novel framework for correctly inferring value function distributions from data, leading to the development of Bayesian Backwards Induction, which is experimentally shown to be competitive with state-of-the-art methods.
Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning. While "model-based" BRL algorithms have focused either on maintaining a posterior distribution on models or value functions and combining this with approximate dynamic programming or tree search, previous Bayesian "model-free" value function distribution approaches implicitly make strong assumptions or approximations. We describe a novel Bayesian framework, Inferential Induction, for correctly inferring value function distributions from data, which leads to the development of a new class of BRL algorithms. We design an algorithm, Bayesian Backwards Induction, with this framework. We experimentally demonstrate that the proposed algorithm is competitive with respect to the state of the art.