Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …

Abstract Safe Reinforcement Learning can be defined as the process of learning policies
that maximize the expectation of the return in problems in which it is important to ensure …

We consider the problem of conditioning a Markov process on a rare event and of
representing this conditioned process by a conditioning-free process, called the effective or …

Risk-sensitive control has received considerable interest since the seminal work of Howard
and Matheson (Howard and Matheson, 1971/72) because of its ability to account for …

Very often when studying non-equilibrium systems one is interested in analysing dynamical
behaviour that occurs with very low probability, so called rare events. In practice, since rare …

We have shown recently that a Markov process conditioned on rare events involving time-
integrated random variables can be described in the long-time limit by an effective Markov …

We study constrained reinforcement learning (CRL) from a novel perspective by setting
constraints directly on state density functions, rather than the value functions considered by …

We introduce and test an algorithm that adaptively estimates large deviation functions
characterizing the fluctuations of additive functionals of Markov processes in the long-time …

In many sequential decision-making problems we may want to manage risk by minimizing
some measure of variability in rewards in addition to maximizing a standard criterion …

Current constrained reinforcement learning (RL) methods guarantee constraint satisfaction
only in expectation, which is inadequate for safety-critical decision problems. Since a …