Learning to Remember the Past by Learning to Predict the Future

Reinforcement Learning; RL; Recurrent; Model-Based; Partial Observability; POMDP; Informed POMDP; Sufficient Statistic; Information State; Asymmetric Learning; World Model

Disciplines :

Computer science

Author, co-author :

Lambrechts, Gaspard ; Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science

Language :

English

Title :

Learning to Remember the Past by Learning to Predict the Future

Publication date :

17 November 2023

Number of pages :

Event name :

VUB Reinforcement Learning Talks

Available on ORBi :

since 17 November 2023

Statistics

Number of views

44 (15 by ULiège)

Number of downloads

45 (8 by ULiège)

More statistics