Abstract In Reinforcement Learning (RL), an agent is guided by the rewards it receives from
the reward function. Unfortunately, it may take many interactions with the environment to …

Reinforcement Learning (RL) algorithms are capable of learning effective behaviours
through trial and error interactions with their environment [40]. The recent combination of …

In this work we investigate on the concept of “restraining bolt”, envisioned in Science Fiction.
Specifically we introduce a novel problem in AI. We have two distinct sets of features …

The standard RL world model is that of a Markov Decision Process (MDP). A basic premise
of MDPs is that the rewards depend on the last state and action only. Yet, many real-world …

Growing interest in reinforcement learning approaches to robotic planning and control raises
concerns of predictability and safety of robot behaviors realized solely through learned …

Abstract In Markov Decision Processes (MDPs), the reward obtained in a state is Markovian,
ie, depends on the last state and action. This dependency makes it difficult to reward more …

Many real-world decision problems have multiple objectives. For example, when choosing a
medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize …

LTLf and LDLf are well-known logics on finite traces. We review PLTLf and PLDLf, their pure-
past versions. These are interpreted backward from the end of the trace towards the …

Many traditional solution approaches to relationally specified decision-theoretic planning
problems (eg, those stated in the probabilistic planning domain description language, or …

Finding optimal policies which maximize long term rewards of Markov Decision Processes
requires the use of dynamic programming and backward induction to solve the Bellman …