81 search results - page 15 / 17 » The Optimal Reward Baseline for Gradient-Based Reinforcement... |
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
We consider the exploration/exploitation problem in reinforcement learning (RL). The Bayesian approach to model-based RL offers an elegant solution to this problem, by considering...
UAI
2003
13 years 9 months ago
2003
Many practitioners who use EM and related algorithms complain that they are sometimes slow. When does this happen, and what can be done about it? In this paper, we study the gener...
NIPS
2008
13 years 9 months ago
2008
Policy gradient (PG) reinforcement learning algorithms have strong (local) convergence guarantees, but their learning performance is typically limited by a large variance in the e...
AAAI
2010
13 years 9 months ago
2010
Embedded systems consisting of collaborating agents capable of interacting with their environment are becoming ubiquitous. It is crucial for these systems to be able to adapt to t...
IJCAI
2007
13 years 9 months ago
2007
A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...