“…Keepaway is a subtask of RoboCup that was put forth as a testbed for machine learning in 2001 [17]. It has since been used for research on temporal difference reinforcement learning with function approximation [46], evolutionary learning [47], relational reinforcement learning [48], behaviour transfer [49,50,51,52,53,54,55], batch reinforcement learning [56] and hierarchical reinforcement learning [57].…”