English

Bilinear value networks

Artificial Intelligence 2023-06-28 v3 Machine Learning

Abstract

The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function. When learning to achieve multiple goals, data efficiency is intimately connected with the generalization of the Q-function to new goals. The de-facto paradigm is to approximate Q(s, a, g) using monolithic neural networks. To improve the generalization of the Q-function, we propose a bilinear decomposition that represents the Q-value via a low-rank approximation in the form of a dot product between two vector fields. The first vector field, f(s, a), captures the environment's local dynamics at the state s; whereas the second component, {\phi}(s, g), captures the global relationship between the current state and the goal. We show that our bilinear decomposition scheme substantially improves data efficiency, and has superior transfer to out-of-distribution goals compared to prior methods. Empirical evidence is provided on the simulated Fetch robot task-suite and dexterous manipulation with a Shadow hand.

Keywords

Cite

@article{arxiv.2204.13695,
  title  = {Bilinear value networks},
  author = {Zhang-Wei Hong and Ge Yang and Pulkit Agrawal},
  journal= {arXiv preprint arXiv:2204.13695},
  year   = {2023}
}
R2 v1 2026-06-24T11:01:53.660Z