This paper endeavors to augment the robustness of offline reinforcement learning (RL) in
scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world …

Reinforcement learning (RL) is increasingly applied in recommending ventilator parameters,
yet existing methods prioritize therapeutic effect over patient safety. This leads to excessive …

Racing demands each vehicle to drive at its physical limits, when any safety infraction could
lead to catastrophic failure. In this work, we study the problem of safe reinforcement learning …

Blame attribution is one of the key aspects of accountable decision making, as it provides
means to quantify the responsibility of an agent for a decision making outcome. In this paper …

Offline reinforcement learning (RL) leverages previously collected data for policy
optimization without any further active exploration. Despite the recent interest in this …

We show that the popular reinforcement learning (RL) strategy of estimating the stateaction
value (Q-function) by minimizing the mean squared Bellman error leads to a regression …

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative
evaluation using observational data can help practitioners understand the generalization …

This paper presents a personalized character recommendation system for Multiplayer
Online Battle Arena (MOBA) games which are considered as one of the most popular online …

We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic
policies in contextual bandits with continuous action spaces. Our work is motivated by …

Value function estimation is an indispensable subroutine in reinforcement learning, which
becomes more challenging in the offline setting. In this paper, we propose Hybrid Value …