Gradient descent temporal difference-difference learning

Rong Zhu, James Murray

Keywords: temporal difference learning, gradient-descent based temporal difference, Off-policy, regularization

Abstract:

Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple convex problems such as linear value function approximation, these algorithms are not guaranteed to be stable. To address this, alternative algorithms that are provably convergent in such cases have been introduced, the most well known being gradient descent temporal difference (GTD) learning. This algorithm and others like it, however, tend to converge much more slowly than conventional temporal difference learning.
In this paper we propose gradient descent temporal difference-difference (Gradient-DD) learning in order to accelerate GTD learning by introducing second-order differences in successive parameter updates.
We investigate this algorithm in the framework of linear value function approximation and analytically showing its improvement over GTD learning. Studying the model empirically on the random walk and Boyan-chain prediction tasks, we find substantial improvement over GTD learning and, in several cases, better performance even than conventional TD learning.

One-sentence Summary: We provide gradient descent temporal difference-difference learning in order to accelerate gradient descent temporal difference learning by introducing second-order differences in successive parameter updates.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=jYwNg6t6T