The Internet can be used to solve pedagogical problems. To give an example, seminars for crowded courses exceeding a hundred participants would not be possible without web-based a...
We present several new algorithms for multiagent reinforcement learning. A common feature of these algorithms is a parameterized, structured representation of a policy or value fu...
Carlos Guestrin, Michail G. Lagoudakis, Ronald Par...
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...
With the popularization of the wireless network, and the progress of mobile computing technology, the efficiency of the hand-held device is better, and its applications are wider....
This paper describes the use of the reflective journal in a computer programming course at the University of South Australia. We describe rationale for the journal relating it to ...