LGCEOCNCJan 27, 2025

Inverse Reinforcement Learning via Convex Optimization

arXiv:2501.15957v2h-index: 29
Originality Synthesis-oriented
AI Analysis

This work provides a more accessible and reliable method for researchers and practitioners in reinforcement learning, though it is incremental as it builds on existing convex formulations.

The authors tackled the inverse reinforcement learning problem by reformulating it as a convex optimization problem using CVXPY, making it more robust and reproducible, and extended it to handle noisy expert demonstrations with theoretical analysis and hyperparameter auto-selection.

We consider the inverse reinforcement learning (IRL) problem, where an unknown reward function of some Markov decision process is estimated based on observed expert demonstrations. In most existing approaches, IRL is formulated and solved as a nonconvex optimization problem, posing challenges in scenarios where robustness and reproducibility are critical. We discuss a convex formulation of the IRL problem (CIRL) initially proposed by Ng and Russel, and reformulate the problem such that the domain-specific language CVXPY can be applied directly to specify and solve the convex problem. We also extend the CIRL problem to scenarios where the expert policy is not given analytically but by trajectory as state-action pairs, which can be strongly inconsistent with optimality, by augmenting some of the constraints. Theoretical analysis and practical implementation for hyperparameter auto-selection are introduced. This note helps the users to easily apply CIRL for their problems, without background knowledge on convex optimization.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes