Temporal Difference Based Actor Critic Learning - Convergence and Neural Implementation.

Dotan Di Castro Dmitry Volkinshtein Ron Meir Temporal Difference Based Actor Critic Learning - Convergence and Neural Implementation. 385-392 2008 NIPS http://books.nips.cc/papers/files/nips21/NIPS2008_0437.pdf conf/nips/2008 db/conf/nips/nips2008.html#CastroVM08