Timezone: »

Proximal Point Imitation Learning
Luca Viano · Angeliki Kamoutsi · Gergely Neu · Igor Krawczuk · Volkan Cevher

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #434
This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the problem and then outline how to leverage classical tools from optimization, in particular, the proximal-point method (PPM) and dual smoothing, for online and offline IL, respectively. Thanks to PPM, we avoid nested policy evaluation and cost updates for online IL appearing in the prior literature. In particular, we do away with the conventional alternating updates by the optimization of a single convex and smooth objective over both cost and $Q$-functions. When solved inexactly, we relate the optimization errors to the suboptimality of the recovered policy. As an added bonus, by re-interpreting PPM as dual smoothing with the expert policy as a center point, we also obtain an offline IL algorithm enjoying theoretical guarantees in terms of required expert trajectories. Finally, we achieve convincing empirical performance for both linear and neural network function approximation.

Author Information

Luca Viano (EPFL)
Angeliki Kamoutsi (ETH Zurich)
Gergely Neu (Universitat Pompeu Fabra)
Igor Krawczuk (EPFL)
Volkan Cevher (EPFL)

More from the Same Authors