RLAF: Reinforcement Learning from Automaton Feedback
By: Mahyar Alinejad , Alvaro Velasquez , Yue Wang and more
Potential Business Impact:
Teaches computers to learn tasks with tricky rules.
Reinforcement Learning (RL) in environments with complex, history-dependent reward structures poses significant challenges for traditional methods. In this work, we introduce a novel approach that leverages automaton-based feedback to guide the learning process, replacing explicit reward functions with preferences derived from a deterministic finite automaton (DFA). Unlike conventional approaches that use automata for direct reward specification, our method employs the structure of the DFA to generate preferences over trajectories that are used to learn a reward function, eliminating the need for manual reward engineering. Our framework introduces a static approach that uses the learned reward function directly for policy optimization and a dynamic approach that involves continuous refining of the reward function and policy through iterative updates until convergence. Our experiments in both discrete and continuous environments demonstrate that our approach enables the RL agent to learn effective policies for tasks with temporal dependencies, outperforming traditional reward engineering and automaton-based baselines such as reward machines and LTL-guided methods. Our results highlight the advantages of automaton-based preferences in handling non-Markovian rewards, offering a scalable, efficient, and human-independent alternative to traditional reward modeling. We also provide a convergence guarantee showing that under standard assumptions our automaton-guided preference-based framework learns a policy that is near-optimal with respect to the true non-Markovian objective.
Similar Papers
Fusing Rewards and Preferences in Reinforcement Learning
Machine Learning (CS)
Teaches robots better by learning from choices.
Inference of Deterministic Finite Automata via Q-Learning
Formal Languages and Automata Theory
Teaches computers to learn patterns from examples.
ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
Artificial Intelligence
Teaches robots new tasks from simple words.