Factorized Spectral Representations (FaStR) Improve Sample Efficiency in Reinforcement Learning

Jul 16, 2026

A new method called FaStR factorizes the transition kernel in reinforcement learning into separate state, action, and next-state encoders using a CP decomposition and a noise contrastive objective. This approach reduces the sample complexity required for representation learning, especially in high-dimensional locomotion tasks. Notably, the learned state encoder can transfer across changes in actuators, requiring only the action encoder to be retrained.

Why it matters: FaStR offers a significant advance in sample-efficient deep reinforcement learning by leveraging the tensor structure of transition dynamics, enabling faster adaptation to new environments or actuators.

Full story at: arXiv Machine Learning ↗