Random variables that stand for cost, loss or damage must be confronted in numerous
situations. Dealing with them systematically for purposes in risk management, optimization …

In this paper we study distributionally robust stochastic programming in a setting where there
is a specified reference probability measure and the uncertainty set of probability measures …

Exponential tilting is a technique commonly used in fields such as statistics, probability,
information theory, and optimization to create parametric distribution shifts. Despite its …

In this paper, we study gap-dependent regret guarantees for risk-sensitive reinforcement
learning based on the entropic risk measure. We propose a novel definition of sub-optimality …

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 …

Modeling the stochastic behavior of interacting agents is key for safe motion planning. In this
paper, we study the interaction of risk-aware agents in a game-theoretical framework. Under …

Entropy is a measure of self-information which is used to quantify information losses.
Entropy was developed in thermodynamics, but is also used to compare probabilities based …

In the field of reinforcement learning there has been recent progress towards safety and high-
confidence bounds on policy performance. However, to our knowledge, no practical …

With the increasing pace of automation, modern robotic systems need to act in stochastic,
non-stationary, partially observable environments. A range of algorithms for finding …

We study the risk-aware reinforcement learning (RL) problem in the episodic finite-horizon
Markov decision process with unknown transition and reward functions. In contrast to the risk …