Timezone: »

 
Poster
Taylor Expansion Policy Optimization
Yunhao Tang · Michal Valko · Remi Munos

Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 06:00 PM -- 06:45 PM (PDT) @ None #None

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.

Author Information

Yunhao Tang (Columbia University)
Michal Valko (DeepMind)
Remi Munos (DeepMind)

More from the Same Authors