TY  - RPRT
TI  - Reinforcement learning with via-point representation.
AU  - Hiroyuki Miyamoto
AU  - Jun Morimoto
AU  - Kenji Doya
AU  - Mitsuo Kawato
PY  - 2004
DO  - 10.1016/j.neunet.2003.11.004
UR  - https://pubmed.ncbi.nlm.nih.gov/15037348/
ID  - 15037348
ER  -