Many potential applications of reinforcement learning (RL) require guarantees that the agent
will perform well in the face of disturbances to the dynamics or reward function. In this paper …

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 …

Over the last two decades, coherent risk measures have been well studied as a principled,
axiomatic way to characterize the risk of a random variable. Because of this axiomatic …

The reinforcement learning algorithms that focus on how to compute the gradient and
choose next actions, are effectively improved the performance of the agents. However, these …