Learning to win process-control games watching game-masters

The present paper focuses on some interesting classes of process-control games, where winning essentially means successfully controlling the process. A master for one of these games is an agent who plays a winning strategy. In this paper we investigate situations in which even a complete model (given by a program) of a particular game does not provide enough information to synthesize—even incrementally—a winning strategy. However, if in addition to getting a program, a machine may also watch masters play winning strategies, then the machine is able to incrementally learn a winning strategy for the given game. Studied are successful learning from arbitrary masters and from pedagogically useful selected masters. It is shown that selected masters are strictly more helpful for learning than are arbitrary masters. Both for learning from arbitrary masters and for learning from selected masters, though, there are cases where one can learn programs for winning strategies from masters but not if one is required to learn a program for the master's strategy itself. Both for learning from arbitrary masters and for learning from selected masters, one can learn strictly more by watching m+1 masters than one can learn by watching only m. Last, a simulation result is presented where the presence of a selected master reduces the complexity from infinitely many semantic mind changes to finitely many syntactic ones.

Cerebellar augmented joint control for a humanoid robot

The joints of a humanoid robot experience disturbances of markedly different magnitudes during the course of a walking gait. Consequently, simple feedback control techniques poorly track desired joint trajectories. This paper explores the addition of a control system inspired by the architecture of the cerebellum to improve system response. This system learns to compensate the changes in load that occur during a cycle of motion. The joint compensation scheme, called Trajectory Error Learning, augments the existing feedback control loop on a humanoid robot. The results from tests on the GuRoo platform show an improvement in system response for the system when augmented with the cerebellar compensator.