Worst-Case Regret Bounds for Exploration via Randomized Value Functions

Abstract

This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. By providing a worst-case regret bound for tabular finite-horizon Markov decision processes, we show that planning with respect to these randomized value functions can induce provably efficient exploration.

References in corpus (2)

• A Bayesian Sampling Approach to Exploration in Reinforcement Learning
• Randomised Bayesian Least-Squares Policy Iteration

Cited by in corpus (6)

• Model-Based Reinforcement Learning with Value-Targeted Regression
• Corruption-robust exploration in episodic reinforcement learning
• Frequentist Regret Bounds for Randomized Least-Squares Value Iteration
• On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces
• MADE: Exploration via Maximizing Deviation from Explored Regions
• Towards Tractable Optimism in Model-Based Reinforcement Learning