%A Zahedi,Keyan %A Martius,Georg %A Ay,Nihat %D 2013 %J Frontiers in Psychology %C %F %G English %K Information-driven self-organisation,Predictive Information,Reinforcement Learning,Embodied Artificial Intelligence,Embodied Machine Learning %Q %R 10.3389/fpsyg.2013.00801 %W %L %M %P %7 %8 2013-November-04 %9 Original Research %+ Dr Keyan Zahedi,Max Planck Institute for Mathematics in the Sciences,Leipzig,Germany,keyan.zahedi@gmail.com %# %! One-step PI & episodic RL %* %< %T Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis %U https://www.frontiersin.org/articles/10.3389/fpsyg.2013.00801 %V 4 %0 JOURNAL ARTICLE %@ 1664-1078