Sciweavers

46 search results - page 4 / 10
» Improve Searching by Reinforcement Learning in Unstructured ...
Sort
View
GECCO
2006
Springer
133views Optimization» more  GECCO 2006»
15 years 1 months ago
On-line evolutionary computation for reinforcement learning in stochastic domains
In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...
Shimon Whiteson, Peter Stone
ICML
1999
IEEE
15 years 10 months ago
Using Reinforcement Learning to Spider the Web Efficiently
Consider the task of exploring the Web in order to find pages of a particular kind or on a particular topic. This task arises in the construction of search engines and Web knowled...
Jason Rennie, Andrew McCallum
88
Voted
ICRA
2009
IEEE
132views Robotics» more  ICRA 2009»
15 years 4 months ago
Smoothed Sarsa: Reinforcement learning for robot delivery tasks
— Our goal in this work is to make high level decisions for mobile robots. In particular, given a queue of prioritized object delivery tasks, we wish to find a sequence of actio...
Deepak Ramachandran, Rakesh Gupta
ATAL
2009
Springer
15 years 4 months ago
Generalized model learning for reinforcement learning in factored domains
Improving the sample efficiency of reinforcement learning algorithms to scale up to larger and more realistic domains is a current research challenge in machine learning. Model-ba...
Todd Hester, Peter Stone
88
Voted
AAAI
2010
14 years 11 months ago
Relative Entropy Policy Search
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature conv...
Jan Peters, Katharina Mülling, Yasemin Altun