lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a r...
Tom Croonenborghs, Karl Tuyls, Jan Ramon, Maurice ...
Developing dialogue systems is a complex process. In particular, designing efficient dialogue management strategies is often difficult as there are no precise guidelines to develo...
There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most...