Reinforcement learning (RL) is one of the most vibrant research frontiers in machine
learning and has been recently applied to solve a number of challenging problems. In this …

Counterfactual estimators enable the use of existing log data to estimate how some new
target recommendation policy would have performed, if it had been used instead of the …

This paper develops the first policy gradient method with global optimality guarantee and
complexity analysis for robust reinforcement learning under model mismatch. Robust …

We consider the problem of learning a control policy that is robust against the parameter
mismatches between the training environment and testing environment. We formulate this as …

Reinforcement learning (RL) has demonstrated remarkable achievements in simulated
environments. However, carrying this success to real environments requires the important …

While reinforcement learning has witnessed tremendous success recently in a wide range of
domains, robustness–or the lack thereof–remains an important issue that remains …

Off-policy evaluation and learning (OPE/L) use offline observational data to make better
decisions, which is crucial in applications where online experimentation is limited. However …

Toward theoretical understandings of robust Markov decision processes: Sample
complexity and asymptotics Page 1 The Annals of Statistics 2022, Vol. 50, No. 6, 3223–3248 …

Methods for bandit learning from user interactions often require a model of the reward a
certain context-action pair will yield–for example, the probability of a click on a …

Modern recommender systems are often modelled under the sequential decision-making
paradigm, where the system decides which recommendations to show in order to maximise …