no code implementations • NeurIPS 2017 • Zhongwen Xu, Joseph Modayil, Hado P. Van Hasselt, Andre Barreto, David Silver, Tom Schaul
Neural networks have a smooth initial inductive bias, such that small changes in input do not lead to large changes in output.
no code implementations • NeurIPS 2014 • A. Rupam Mahmood, Hado P. Van Hasselt, Richard S. Sutton
Second, we show that these benefits extend to a new weighted-importance-sampling version of off-policy LSTD(lambda).