CORL: A Continuous-state Offset-dynamics Reinforcement Learner

Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct with a sample complexity that scales polynomially with the state-space dimension. Unfortunately, no optimal planning techniques exist in general for such problems; instead we use fitted value iteration to solve the learned MDP, and include the error due to approximate planning in our bounds. Finally, we report an experiment using a robotic car driving over varying terrain to demonstrate that these dynamics representations adequately capture real-world dynamics and that our algorithm can be used to efficiently solve such problems.

• Type: Conference
• Year: 2008
• Where: UAI
• Authors: Emma Brunskill, Bethany R. Leffler, Lihong Li, Michael L. Littman, Nicholas Roy
• Keywords: Artificial Intelligence, Continuous State Spaces, Probably Approximately Correct, Switching Dynamics, UAI 2008