Timezone: »

Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach
Michael Gimelfarb · Scott Sanner · Chi-Guhn Lee

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #127

Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms. Typically, such information includes an estimate of the optimal value function and is often provided by a human expert or other sources of domain knowledge. However, this information is often biased or inaccurate and can mislead many reinforcement learning algorithms. In this paper, we apply Bayesian Model Combination with multiple experts in a way that learns to trust a good combination of experts as training progresses. This approach is both computationally efficient and general, and is shown numerically to improve convergence across discrete and continuous domains and different reinforcement learning algorithms.

Author Information

Michael Gimelfarb (University of Toronto)
Scott Sanner (University of Toronto)
Chi-Guhn Lee (University of Toronto)

More from the Same Authors