On Connections between Constrained Optimization and Reinforcement Learning
This work provides a theoretical framework for RL researchers to potentially develop more efficient algorithms, but it is incremental as it consolidates existing scattered connections.
The paper connects dynamic programming schemes in reinforcement learning to convex optimization algorithms, linking specific methods like Conservative Policy Iteration to Frank-Wolfe, aiming to inspire new RL algorithm designs.
Dynamic Programming (DP) provides standard algorithms to solve Markov Decision Processes. However, these algorithms generally do not optimize a scalar objective function. In this paper, we draw connections between DP and (constrained) convex optimization. Specifically, we show clear links in the algorithmic structure between three DP schemes and optimization algorithms. We link Conservative Policy Iteration to Frank-Wolfe, Mirror-Descent Modified Policy Iteration to Mirror Descent, and Politex (Policy Iteration Using Expert Prediction) to Dual Averaging. These abstract DP schemes are representative of a number of (deep) Reinforcement Learning (RL) algorithms. By highlighting these connections (most of which have been noticed earlier, but in a scattered way), we would like to encourage further studies linking RL and convex optimization, that could lead to the design of new, more efficient, and better understood RL algorithms.