5 papers
Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs
Lorenzo Pantè, Andrea Fanti, Roberto Capobianco
Open-ended curricula in Reinforcement Learning (RL) aim to train generally-capable agents by identifying tasks that facilitate learning increasingly complex skills. A major challen…
DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications
Elena Umili, Francesco Argenziano, Roberto Capobianco
Integrating logical knowledge into deep neural network training is still a hard challenge, especially for sequential or temporally extended domains involving subsymbolic observatio…
Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization
Matteo Pannacci, Andrea Fanti, Elena Umili +1
In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symboli…
Neural Reward Machines
Elena Umili, Francesco Argenziano, Roberto Capobianco
Non-markovian Reinforcement Learning (RL) tasks are very hard to solve, because agents must consider the entire history of state-action pairs to act rationally in the environment.…
DeepDFA: Automata Learning through Neural Probabilistic Relaxations
Elena Umili, Roberto Capobianco
In this work, we introduce DeepDFA, a novel approach to identifying Deterministic Finite Automata (DFAs) from traces, harnessing a differentiable yet discrete model. Inspired by bo…