On Average Versus Discounted Reward Temporal-Difference Learning
Machine Learning
Long-term reward prediction in TD models of the dopamine system
Neural Computation
Temporal Difference Model Reproduces Anticipatory Neural Activity
Neural Computation
Brief paper: Average cost temporal-difference learning
Automatica (Journal of IFAC)
Hi-index | 0.01 |
Hyperbolic discounting of future outcomes is widely observed to underlie choice behavior in animals. Additionally, recent studies (Kobayashi & Schultz, 2008) have reported that hyperbolic discounting is observed even in neural systems underlying choice. However, the most prevalent models of temporal discounting, such as temporal difference learning, assume that future outcomes are discounted exponentially. Exponential discounting has been preferred largely because it can be expressed recursively, whereas hyperbolic discounting has heretofore been thought not to have a recursive definition. In this letter, we define a learning algorithm, hyperbolically discounted temporal difference (HDTD) learning, which constitutes a recursive formulation of the hyperbolic model.