We present a new behavioural distance over the state space of a Markov decision process,
and demonstrate the use of this distance as an effective means of shaping the learnt …

In computer science, reinforcement learning is a powerful framework with which artificial
agents can learn to maximize their performance for any given Markov decision process …

Although the notion of task similarity is potentially interesting in a wide range of areas such
as curriculum learning or automated planning, it has mostly been tied to transfer learning …

Self-adaptive systems provide the ability of autonomous decision-making for handling the
changes affecting the functionalities of cyber-physical systems. A self-adaptive system …

Recent advances in reinforcement-learning research have demonstrated impressive results
in building algorithms that can out-perform humans in complex tasks. Nevertheless, creating …

In this thesis we investigate the problem of reinforcement learning in partially observed and
multi-agent systems. The belief state, which is the most common information state used in …

This paper proposes a novel deep reinforcement learning (RL) architecture, which learns a
dynamics model in latent space that is behaviorally grounded to the observed space and …

The framework of reinforcement learning is a powerful suite of algorithms that can learn
generalized solutions to complex decision making problems. However, the applications of …