On the Convergence of Smooth Regularized Approximate Value Iteration Schemes

NeurIPS 2020 • Elena Smirnova • Elvis Dohmatob

Entropy regularization, smoothing of Q-values and neural network function approximator are key components of the state-of-the-art reinforcement learning (RL) algorithms, such as Soft Actor-Critic~\cite{haarnoja2018soft}. Despite the widespread use, the impact of these core techniques on the convergence of RL algorithms is not yet fully understood... (read more)

PDF Abstract