/torch-policy-gradient

Deterministic Policy Gradient using torch7

Primary LanguageJupyter NotebookOtherNOASSERTION

Single pendulum Deterministic Policy Gradient example using torch7

Continuous Control with Deep Reinforcement Learning

Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra

http://arxiv.org/abs/1509.02971

Dependecies

luarocks install Math-RungeKutta
luarocks install csvigo
luarocks install image
luarocks install hdf5

Implemented by Yannis M. Assael (yannisassael.com)