Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning

Marek Grzes, Daniel Kudenko

Research output: Contribution to conferencePaperpeer-review


Reinforcement learning suffers scalability problems due to the state space explosion and the temporal credit assignment problem. Knowledge-based approaches have received a significant attention in the area. Reward shaping is a particular approach to incorporate domain knowledge into reinforcement learning. Theoretical and empirical analysis of this paper reveals important properties of this principle, especially the influence of the reward type, MDP discount factor, and the way of evaluating the potential function on the performance.
Original languageUndefined/Unknown
Publication statusPublished - 2009

Cite this