Poster

Taylor Expansion Policy Optimization

Yunhao Tang · Michal Valko · Remi Munos

Keywords: [ Deep Reinforcement Learning ] [ Reinforcement Learning ] [ Reinforcement Learning - Deep RL ]

[ Abstract ] [ Join Zoom
Please do not share or post zoom links

Abstract:

In this work, we investigate the application of Taylor expansions in reinforcement learning. In particular, we propose Taylor Expansion Policy Optimization, a policy optimization formalism that generalizes prior work as a first-order special case. We also show that Taylor expansions intimately relate to off-policy evaluation. Finally, we show that this new formulation entails modifications which improve the performance of several state-of-the-art distributed algorithms.

Chat is not available.