History Compression via Language Models in Reinforcement Learning

Fabian Paischer, Thomas Adler, Vihang P. Patil, Angela Bitto-Nemling, Markus Holzleitner, Sebastian Lehner, Hamid Eghbal-Zadeh, Sepp Hochreiter

Abstract: In a partially observable Markov decision process (POMDP), an agent typically uses a representation of the past to approximate the underlying MDP. We propose to utilize a frozen Pretrained Language...