In the future, powerful AI systems may be deployed in high-stakes settings, where a single
failure could be catastrophic. One technique for improving AI safety in high-stakes settings is …

Abstract Inverse Constraint Reinforcement Learning (ICRL) aims to recover the underlying
constraints respected by expert agents in a data-driven manner. Existing ICRL algorithms …

Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the
inverse reinforcement learning problem. Unfortunately current methods generally do not …

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 …

Markov decision processes (MDPs) often suffer from the sensitivity issue under model
ambiguity. In recent years, robust MDPs have emerged as an effective framework to …

Abstract Risk-averse Markov Decision Processes (MDPs) have optimal policies that achieve
high returns with low variability, but these MDPs are often difficult to solve. Only a few …

Advances in robotic skill acquisition have made it possible to build general-purpose libraries
of learned skills for downstream manipulation tasks. However, naively executing these skills …

Integrated task and motion planning (TAMP) has proven to be a valuable approach to
generalizable long-horizon robotic manipulation and navigation problems. However, the …

Practical implementations of deep reinforcement learning (deep RL) have been challenging
due to an amplitude of factors, such as designing reward functions that cover every possible …

The difficulty in specifying rewards for many real-world problems has led to an increased
focus on learning rewards from human feedback, such as demonstrations. However, there …