Sciweavers

Share
10 search results - page 1 / 2
» Near-optimal Regret Bounds for Reinforcement Learning
Sort
View
ML
2002
ACM
121views Machine Learning» more  ML 2002»
11 years 29 days ago
Near-Optimal Reinforcement Learning in Polynomial Time
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...
Michael J. Kearns, Satinder P. Singh
COLT
2010
Springer
10 years 11 months ago
An Asymptotically Optimal Bandit Algorithm for Bounded Support Models
Multiarmed bandit problem is a typical example of a dilemma between exploration and exploitation in reinforcement learning. This problem is expressed as a model of a gambler playi...
Junya Honda, Akimichi Takemura
CORR
2010
Springer
105views Education» more  CORR 2010»
10 years 12 months ago
Optimism in Reinforcement Learning Based on Kullback-Leibler Divergence
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
Sarah Filippi, Olivier Cappé, Aurelien Gari...
AAAI
2004
11 years 2 months ago
Performance Bounded Reinforcement Learning in Strategic Interactions
Despite increasing deployment of agent technologies in several business and industry domains, user confidence in fully automated agent driven applications is noticeably lacking. T...
Bikramjit Banerjee, Jing Peng
books