Up: Sequential Decision Making Based
Thanks to Sepp Hochreiter, Jieyu Zhao,
Nic Schraudolph, Fred Cummins, Luca Gambardella
for valuable comments. This work was supported in part
by SNF grant 21-43'417.95 ``Incremental Self-Improvement'' and SNF
grant 2100-49'144.96 ``Long Short-Term Memory''.
Back to Reinforcement Learning and POMDP page