TY  - JOUR

T1  - Spike-based reinforcement learning in continuous state and action space: when policy gradient methods fail

JO  - PLoS Comput Biol

UR  - http://eprints.whiterose.ac.uk/99461/

PY  - 2009/12/01

AU  - Vasilaki E

AU  - Frémaux N

AU  - Urbanczik R

AU  - Senn W

AU  - Gerstner W

ED  - 

DO  - DOI: 10.1371/journal.pcbi.1000586

VL  - 5

IS  - 12

SP  - e1000586

Y2  - 2024/10/23

ER  -