Výsledky vyhledávání - "Hepburn, Charles A."

Report

State-Constrained Offline Reinforcement Learning

Autor: Hepburn, Charles A., Jin, Yue, Montana, Giovanni

Traditional offline reinforcement learning methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of distributional shift but res

Externí odkaz: http://arxiv.org/abs/2405.14374

Zobrazit plný text záznamu

Report

Model-based trajectory stitching for improved behavioural cloning and its applications

Autor: Hepburn, Charles A., Montana, Giovanni

Behavioural cloning (BC) is a commonly used imitation learning method to infer a sequential decision-making policy from expert demonstrations. However, when the quality of the data is not optimal, the resulting behavioural policy also performs sub-op

Externí odkaz: http://arxiv.org/abs/2212.04280

Zobrazit plný text záznamu

Report

Model-based Trajectory Stitching for Improved Offline Reinforcement Learning

Autor: Hepburn, Charles A., Montana, Giovanni

In many real-world applications, collecting large and high-quality datasets may be too costly or impractical. Offline reinforcement learning (RL) aims to infer an optimal decision-making policy from a fixed set of data. Getting the most information f

Externí odkaz: http://arxiv.org/abs/2211.11603

Zobrazit plný text záznamu