Inverse Reinforcement Learning in the Continuous Setting with Formal Guarantees

Dexter, Gregory, Bello, Kevin, Honorio, Jean

arXiv.org Machine Learning 

Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior. IRL is useful for automated control in situations where the reward function is difficult to specify manually, which impedes reinforcement learning. We provide a new IRL algorithm for the continuous state space setting with unknown transition dynamics by modeling the system using a basis of orthonormal functions. We provide a proof of correctness and formal guarantees on the sample and time complexity of our algorithm.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found