Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Temporal-Causal Inference for Reinforcement Learning via Automata Learning
Jan Corazza, Daniil Kaminskyi, Simon Lutz +4
We consider reinforcement learning in environments with dynamics that undergo an irreversible phase transition governed by a hidden temporal pattern. The agent observes the base st…
cs.LG2023
Unsupervised Automata Learning via Discrete Optimization
Simon Lutz, Daniil Kaminskyi, Florian Wittbold +5
Automata learning is a successful tool for many application domains such as robotics and automatic verification. Typically, automata learning techniques operate in a supervised lea…