This is a cached version of the website. Click here to view the live site.

Enjoying our site? Please disable your ad blocker to support us!

Academic Torrents

Browse
- Datasets
- Papers
- Courses
- Collections
Upload
About
Support
Login

Near-optimal Regret Bounds for Reinforcement Learning
Peter Auer and Thomas Jaksch and Ronald Ortner

Home
Technical 2/0
Comments 0
Collections
0
I accept the terms Download 358.46kB

Near-optimal Regret Bounds for Reinforcement Learning.pdf	358.46kB

Type: Paper

Tags:

Bibtex:

@article{11:51,author={Thomas Jaksch and Ronald Ortner and Peter Auer}, Title={Near-optimal Regret Bounds for Reinforcement Learning},journal={Journal of Machine Learning Research},volume={11}, url={http://www.jmlr.org/papers/volume11/jaksch10a/jaksch10a.pdf}}

No stats to report yet.

Related Torrents

Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
309.45kB · 2 seeds
Data-dependent margin-based generalization bounds for classification
298.60kB · 3 seeds
Multi-Agent Reinforcement Learning in Common Interest and Fixed Sum Stochastic Games: An Experime...
31.04kB · 2 seeds
Value Function Based Reinforcement Learning in Changing Markovian Environments
382.70kB · 2 seeds
Finding Optimal Bayesian Network Given a Super-Structure
356.67kB · 2 seeds

Send Feedback

We are a community-maintained distributed repository for datasets and scientific knowledge
About - Terms - DB - RSS