BibSonomy publications for /user/idsia/artificial,Tue Mar 11 14:52:34 CET 2008Proc. 5th European Workshop on Reinforcement Learning (EWRL-5)27--29Gradient-based Reinforcement Planning in Policy-Search Methods272001juergen, intelligence, decent, search gradient, reinforcement, direct, planning, artificial, policy, learning, Tue Mar 11 14:52:34 CET 2008Proc. 5th European Workshop on Reinforcement Learning (EWRL-5)25--26Universal Sequential Decisions in Unknown Environments272001artificial, intelligence, sequential, induction, rational, kolmogorov, theory, solomonoff, agents, complexity, learning, reinforcement, algorithmic, juergen, probability, decision, universal computational,