Variance-Based Rewards for Approximate Bayesian Reinforcement Learning

Understand

The explore{exploit dilemma is one of the central challenges in Reinforcement Learning (RL).

• Bayesian RL solves the dilemma by providing the agent with information in the form of a prior distribution over environments; however, full Bayesian planning is intractable.
• Planning with the mean MDP is a common myopic approximation of Bayesian planning.
• We derive a novel reward bonus that is a function of the posterior distribution over environments, which, when added to the reward in planning with the mean MDP, results in an agent which explores efficiently and effectively.