Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines

Deep reinforcement learning (deep RL) excels in various domains but lacks generalizability and interpretability. On the other hand, programmatic RL methods (Trivedi et al., 2021; Liu et al., 2023) reformulate RL tasks as synthesizing interpretable programs that can be executed in the environments. Despite encouraging results, these methods are limited to short-horizon tasks. On the other hand, representing RL policies using state machines (Inala et al., 2020) can inductively generalize to long-horizon tasks; however, it struggles to scale up to …

cs.ai cs.lg cs.pl cs.ro deep rl domains environments horizon interpretability machine machines policy programmatic reinforcement reinforcement learning state synthesis tasks