Implicit Temporal Differences
Tamar, Aviv, Toulis, Panos, Mannor, Shie, Airoldi, Edoardo M.
In reinforcement learning, the TD($\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\lambda$) is its sensitivity to the choice of the step-size. It is an empirically well-known fact that a large step-size leads to fast convergence, at the cost of higher variance and risk of instability. In this work, we introduce the implicit TD($\lambda$) algorithm which has the same function and computational cost as TD($\lambda$), but is significantly more stable. We provide a theoretical explanation of this stability and an empirical evaluation of implicit TD($\lambda$) on typical benchmark tasks. Our results show that implicit TD($\lambda$) outperforms standard TD($\lambda$) and a state-of-the-art method that automatically tunes the step-size, and thus shows promise for wide applicability.
Dec-21-2014
- Country:
- North America > United States
- Massachusetts > Middlesex County > Cambridge (0.14)
- Asia > Middle East
- Israel (0.15)
- North America > United States
- Genre:
- Research Report > New Finding (0.54)
- Technology: