The goal of Reinforcement learning (RL) is to maximize reward (minimize cost) in a Markov decision process (MDP) without knowing the underlying model a priori. RL algorithms tend ...
Under Legg’s and Hutter’s formal measure [1], performance in easy environments counts more toward an agent’s intelligence than does performance in difficult environments. An ...
Cloth modeling and recognition is an important and challenging problem in both vision and graphics tasks, such as dressed human recognition and tracking, human sketch and portrait...
Mediation is the process of decomposing a task into subtasks, finding agents suitable for these subtasks and negotiating with agents to obtain commitments to execute these subtas...
We present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach i...