—Multi-robot reinforcement learning is a very challenging area due to several issues, such as large state spaces, difficulty in reward assignment, nondeterministic action selecti...
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Recent multi-agent extensions of Q-Learning require knowledge of other agents’ payoffs and Q-functions, and assume game-theoretic play at all times by all other agents. This pap...
Learning can be an effective way for robot systems to deal with dynamic environments and changing task conditions. However, popular singlerobot learning algorithms based on discou...
To solve the sparsity problem in collaborative filtering, researchers have introduced transfer learning as a viable approach to make use of auxiliary data. Most previous transfer...