linear function approximation
A method of estimating complex functions using linear combinations of input features, often employed to simplify computations in reinforcement learning.
- A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation
- Computational Hardness of Reinforcement Learning with Partial $q^{\pi}$-Realizability
- Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems
- Scalable Policy-Based RL Algorithms for POMDPs