10 search results - page 2 / 2 » Near-optimal Regret Bounds for Reinforcement Learning |
ICML
2006
IEEE
14 years 9 months ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
ML
2002
ACM
13 years 8 months ago
2002
ACM
Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find profitable actions while t...
ATAL
2006
Springer
14 years 8 days ago
2006
Springer
Factored representations, model-based learning, and hierarchies are well-studied techniques for improving the learning efficiency of reinforcement-learning algorithms in large-sca...
JMLR
2012
11 years 11 months ago
2012
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
CIMCA
2008
IEEE
14 years 3 months ago
2008
IEEE
Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, ...