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 …

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the
uncertainty in model parameters. Parameter uncertainty commonly occurs in many real …

In many sequential decision-making problems one is interested in minimizing an expected
cumulative cost while taking into account risk, ie, increased awareness of events of small …

Abstract The Robust Markov Decision Process (RMDP) framework focuses on designing
control policies that are robust against the parameter uncertainties due to the mismatches …

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

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

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 …

We study risk-sensitive reinforcement learning (RL) based on the entropic risk measure.
Although existing works have established non-asymptotic regret guarantees for this …

In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states
are those states entering which is undesirable or dangerous. We define the risk with respect …