Policy Search by Dynamic Programming

We consider the policy search approach to reinforcement learning. We show that if a “baseline distribution” is given (indicating roughly how often we expect a good policy to visit each state), then we can derive a policy search algorithm that terminates in a finite number of steps, and for which we can provide non-trivial performance guarantees. We also demonstrate this algorithm on several grid-world POMDPs, a planar biped walking robot, and a double-pole balancing problem.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: J. Andrew Bagnell, Sham Kakade, Andrew Y. Ng, Jeff G. Schneider
• Keywords: NIPS 2003, NIPS 2007, Policy Search, Policy Search Algorithm, Policy Search Approach