GitHub

q-function-approximation

This material describe the Q-function approximator for DQN/DDQN and the policy-value network used in PPO. Key components include experience replay and target network updates for DQN-based methods, and ...
IEEE

Gaussian Q Function Approximation in Wireless Communication System’s Design: A Gradient-Based Optimization Approach

Abstract: This paper proposes a novel iterative gradient-based optimization approach aimed at achieving more precise and streamlined approximations for the Gaussian Q function—an essential element in ...
Microsoft

In-Context Compositional Q-Learning for Offline Reinforcement Learning

Accurately estimating the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a single global Q-function, which struggles to capture the ...