Association for the Advancement of Artificial Intelligence
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.
Furelos-Blanco D, Law,M, Russo A, Broda K, Jonsson A. Induction of Subgoal Automata for Reinforcement Learning.. Dins: AA. VV.. Proceedings AAAI 2020. 1 ed. Association for the Advancement of Artificial Intelligence; 2020. p. 3890-3897.