When faced with sequential decision-making problems, it is often useful to be able to predict
what would happen if decisions were made using a new policy. Those predictions must …

Importance Sampling (IS) is a widely used building block for a large variety of off-policy
estimation and learning algorithms. However, empirical and theoretical studies have …

Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by
minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we …

How can we effectively exploit the collected samples when solving a continuous control task
with Reinforcement Learning? Recent results have empirically demonstrated that multiple …

Indirect experiments provide a valuable framework for estimating treatment effects in
situations where conducting randomized control trials (RCTs) is impractical or unethical …

Off-policy methods are the basis of a large number of effective Policy Optimization (PO)
algorithms. In this setting, Importance Sampling (IS) is typically employed for off-policy …

Abstract Goal-conditioned Reinforcement Learning (RL) aims at learning optimal policies,
given goals encoded in special command inputs. Here we study goal-conditioned neural …

Learning in a lifelong setting, where the dynamics continually evolve, is a hard challenge for
current reinforcement learning algorithms. Yet this would be a much needed feature for …

Distribution drift is an important issue for practical applications of machine learning (ML). In
particular, in streaming ML, the data distribution may change over time, yielding the problem …

Delays are inherent to most dynamical systems. Besides shifting the process in time, they
can significantly affect their performance. For this reason, it is usually valuable to study the …