EUBRL: Epistemic Uncertainty Directed Bayesian Reinforcement Learning
By: Jianfei Ma, Wee Sun Lee
At the boundary between the known and the unknown, an agent inevitably confronts the dilemma of whether to explore or to exploit. Epistemic uncertainty reflects such boundaries, representing systematic uncertainty due to limited knowledge. In this paper, we propose a Bayesian reinforcement learning (RL) algorithm, $\texttt{EUBRL}$, which leverages epistemic guidance to achieve principled exploration. This guidance adaptively reduces per-step regret arising from estimation errors. We establish nearly minimax-optimal regret and sample complexity guarantees for a class of sufficiently expressive priors in infinite-horizon discounted MDPs. Empirically, we evaluate $\texttt{EUBRL}$ on tasks characterized by sparse rewards, long horizons, and stochasticity. Results demonstrate that $\texttt{EUBRL}$ achieves superior sample efficiency, scalability, and consistency.
Similar Papers
Online Bayesian Risk-Averse Reinforcement Learning
Machine Learning (CS)
Teaches computers to learn safely from less data.
Quantum-Inspired Reinforcement Learning in the Presence of Epistemic Ambivalence
Machine Learning (CS)
Helps computers make good choices with mixed-up info.
Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models
Machine Learning (CS)
Teaches computers to learn faster from experience.