Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Generalization in Planning (GenPlan '23)

Inverse Reinforcement Learning with Multiple Planning Horizons

Jiayu Yao · Finale Doshi-Velez · Barbara Engelhardt

Keywords: [ inverse reinforcement learning ] [ identifiability ] [ Generalizability ]


Abstract:

In this work, we study an inverse reinforcement learning (IRL) problem where the experts are planning under a shared reward function but with different planning horizons. Without the knowledge of discount factors, the reward function has a larger feasible solution set, which makes it harder to identify a reward function. To overcome the challenge, we develop an algorithm that in practice, can learn a reward function similar to the true reward function. We give an empirical characterization of the identifiability and generalizability of the feasible solution set of the reward function.

Chat is not available.