Reinforcement learning (RL) with linear temporal logic (LTL) objectives can allow robots to
carry out symbolic event plans in unknown environments. Most existing methods assume …

Reward machines (RMs) are a recent formalism for representing the reward function of a
reinforcement learning task through a finite-state machine whose edges encode subgoals of …

Temporal logic (TL) tasks consist of complex and temporally extended subgoals and they
are common for many real-world applications, such as service and navigation robots …

Many important real-world Reinforcement Learning (RL) problems involve partial
observability and require policies with memory. Unfortunately, standard deep RL algorithms …

A critical challenge in neuro-symbolic (NeSy) approaches is to handle the symbol grounding
problem without direct supervision. That is mapping high-dimensional raw data into an …

This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for
reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM …

Discrete optimization problems appear in everyday life, with a wide range of applications
including airline scheduling, telecommunications network design and healthcare. Modern …

Reinforcement learning (RL) with non-Markovian rewards requires agents to learn
historydependent policies, which is particularly challenging in long-horizon or sparse reward …

Deep learning and symbolic artificial intelligence remain the two main paradigms in Artificial
Intelligence (AI), each presenting their own strengths and weaknesses. Artificial agents …

Temporal logic (TL) tasks consist of complex and temporally extended subgoals and they
are common for many real-world applications, such as service and navigation robots …