34 search results - page 1 / 7 » Towards Finite-Sample Convergence of Direct Reinforcement Le... |
ECML
2005
Springer
14 years 4 months ago
2005
Springer
Abstract. While direct, model-free reinforcement learning often performs better than model-based approaches in practice, only the latter have yet supported theoretical guarantees f...
NIPS
1998
14 years 7 days ago
1998
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...
ICML
1996
IEEE
14 years 3 months ago
1996
IEEE
This paper presents a direct reinforcement learning algorithm, called Finite-Element Reinforcement Learning, in the continuous case, i.e. continuous state-space and time. The eval...
IJCAI
2001
14 years 8 days ago
2001
Most formulations of Reinforcement Learning depend on a single reinforcement reward value to guide the search for the optimal policy solution. If observation of this reward is rar...
ESAW
2008
Springer
14 years 20 days ago
2008
Springer
Reactive multi-agent systems present global behaviours uneasily linked to their local dynamics. When it comes to controlling such a system, usual analytical tools are difficult to ...