Multi-objective reinforcement learning (MORL) has been proposed to learn control policies
over multiple competing objectives with each possible preference over returns. However …

We propose a novel multi-objective reinforcement learning algorithm that successfully learns
the optimal policy even for non-linear utility functions. Non-linear utility functions pose a …

In many risk-aware and multi-objective reinforcement learning settings, the utility of the user
is derived from a single execution of a policy. In these settings, making decisions based on …

Abstract The Internet of Things (IoT IoT) is built on a foundation of wireless sensor devices
that connect humans and physical objects to the Internet and enable them to interact with …

For effective decision support in scenarios with conflicting objectives, sets of potentially
optimal solutions can be presented to the decision maker. We explore both what policies …

In sequential multi-objective decision making (MODeM) settings, when the utility of a user is
derived from a single execution of a policy, policies for the expected scalarised returns …

Many real-world problems contain multiple objectives and agents, where a trade-off exists
between objectives. Key to solving such problems is to exploit sparse dependency …

In this paper, we focus on multi-objective reinforcement learning (RL) where the expected
vector returns are aggregated with a concave function. For this generic framework, which …

In sequential multi-objective decision making (MODeM) settings, when the utility of a user is
derived from a single execution of a policy, policies for the expected scalarised returns …

If widespread deployment of AI systems is to be accepted by society in the future, it is crucial
that such systems are trustworthy. Trustworthiness for autonomous systems has a number of …