Induction of Subgoal Automata for Reinforcement Learning


  • Daniel Furelos-Blanco Imperial College London
  • Mark Law Imperial College London
  • Alessandra Russo Imperial College London
  • Krysia Broda Imperial College London
  • Anders Jonsson Universitat Pompeu Fabra



In this work we present ISA, a novel approach for learning and exploiting subgoals in reinforcement learning (RL). Our method relies on inducing an automaton whose transitions are subgoals expressed as propositional formulas over a set of observable events. A state-of-the-art inductive logic programming system is used to learn the automaton from observation traces perceived by the RL agent. The reinforcement learning and automaton learning processes are interleaved: a new refined automaton is learned whenever the RL agent generates a trace not recognized by the current automaton. We evaluate ISA in several gridworld problems and show that it performs similarly to a method for which automata are given in advance. We also show that the learned automata can be exploited to speed up convergence through reward shaping and transfer learning across multiple tasks. Finally, we analyze the running time and the number of traces that ISA needs to learn an automata, and the impact that the number of observable events have on the learner's performance.




How to Cite

Furelos-Blanco, D., Law, M., Russo, A., Broda, K., & Jonsson, A. (2020). Induction of Subgoal Automata for Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 3890-3897.



AAAI Technical Track: Machine Learning