A Short Survey on Probabilistic Reinforcement Learning
It provides a concise overview for researchers and practitioners needing performance guarantees in reinforcement learning, but it is incremental as a survey.
The paper surveys methods for balancing exploration-exploitation and computing robust solutions from fixed samples in reinforcement learning, particularly for sensitive domains where data collection is limited.
A reinforcement learning agent tries to maximize its cumulative payoff by interacting in an unknown environment. It is important for the agent to explore suboptimal actions as well as to pick actions with highest known rewards. Yet, in sensitive domains, collecting more data with exploration is not always possible, but it is important to find a policy with a certain performance guaranty. In this paper, we present a brief survey of methods available in the literature for balancing exploration-exploitation trade off and computing robust solutions from fixed samples in reinforcement learning.