Richard S. Sutton, Joseph Modayil, Michael Delp, Thomas Degris, Patrick M. Pilarski, Adam White, and Doina PrecupHorde (2011), A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction, Proc. of 10th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011), Tumer, Yolum, Sonenberg and Stone (eds.), May, 2–6, 2011, Taipei, Taiwan, pp. 761-768.
Maintaining accurate world knowledge in a complex and changing environment is a perennial problem for robots and other artificial intelligence systems. Our architecture for addressing this problem, called Horde, consists of a large number of independent reinforcement learning sub-agents, or demons. Each demon is responsible for answering a single predictive or goal-oriented question about the world, thereby contributing in a factored, modular way to the system’s overall knowledge. The questions are in the form of a value function, but each demon has its own policy, reward function, termination function, and terminal-reward function unrelated to those of the base problem. Learning proceeds in parallel by all demons simultaneously so as to extract the maximal training information from whatever actions are taken by the system as a whole. Gradient-based temporal-difference learning methods are used to learn efficiently and reliably with function approximation in this off-policy setting. Horde runs in constant time and memory per time step, and is thus suitable for learning online in realtime applications such as robotics. We present results using Horde on a multi-sensored mobile robot to successfully learn goal-oriented behaviors and long-term predictions from off-policy experience. Horde is a significant incremental step towards a real-time architecture for efficient learning of general knowledge from unsupervised sensorimotor interaction.