Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces

1 code implementation • 24 May 2024 • Angeliki Kamoutsi, Peter Schmitt-Förster, Tobias Sutter, Volkan Cevher, John Lygeros

This work studies discrete-time discounted Markov decision processes with continuous state and action spaces and addresses the inverse problem of inferring a cost function from observed optimal behavior.

Proximal Point Imitation Learning

2 code implementations • 22 Sep 2022 • Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher

Thanks to PPM, we avoid nested policy evaluation and cost updates for online IL appearing in the prior literature.

Imitation Learning

Stochastic convex optimization for provably efficient apprenticeship learning

no code implementations • 31 Dec 2021 • Angeliki Kamoutsi, Goran Banjac, John Lygeros

We consider large-scale Markov decision processes (MDPs) with an unknown cost function and employ stochastic convex optimization tools to address the problem of imitation learning, which consists of learning a policy from a finite set of expert demonstrations.

Imitation Learning reinforcement-learning +1

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

no code implementations • 28 Dec 2021 • Angeliki Kamoutsi, Goran Banjac, John Lygeros

We consider large-scale Markov decision processes with an unknown cost function and address the problem of learning a policy from a finite set of expert demonstrations.

reinforcement-learning Reinforcement Learning (RL)