Optimization
Fast Algorithms for L-Constrained S-Rectangular Robust MDPs
Robust Markov decision processes (RMDPs) are a useful building block of robust reinforcement learning algorithms but can be hard to solve.
Reward is Enough for Convex MDPs
Maximising a cumulative reward function that is Markov and stationary, i.e., defined over state-action pairs and independent of time, is sufficient to capture many
Reward is Enough for Convex MDPs
Maximising a cumulative reward function that is Markov and stationary, i.e., defined over state-action pairs and independent of time, is sufficient to capture many
Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
In this setting, the learner receives context (e.g., weather conditions) at each round, and has to choose an action (e.g., turbine parameters).
Fast Training Methods for Stochastic Compositional Optimization Problems Hongchang Gao
Thus, it is necessary to develop efficient methods for its optimization.