Loading...
Please wait, while we are loading the content...
Similar Documents
The Epoch-Greedy algorithm for contextual multi-armed bandits
| Content Provider | Semantic Scholar |
|---|---|
| Author | Langford, John Zhang, Tong |
| Copyright Year | 2007 |
| Abstract | We present Epoch-Greedy, an algorithm for contextual multi-armed bandits (also known as bandits with side information). Epoch-Greedy has the following properties: 1. No knowledge of a time horizon T is necessary. 2. The regret incurred by Epoch-Greedy is controlled by a sample complexity bound for a hypothesis class. 3. The regret scales as O(T2/3S1/3) or better (sometimes, much better). Here S is the complexity term in a sample complexity bound for standard supervised learning. |
| Starting Page | 817 |
| Ending Page | 824 |
| Page Count | 8 |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.stat.rutgers.edu/home/tzhang/papers/nips07-bandits.pdf |
| Alternate Webpage(s) | http://stat.rutgers.edu/home/tzhang/papers/nips07-bandits.pdf |
| Alternate Webpage(s) | http://hunch.net/~jl/projects/RL/sidebandits/bandit.pdf |
| Alternate Webpage(s) | http://courses.cms.caltech.edu/cs101.2/slides/cs101.2-05-contextual-bandits.pdf |
| Alternate Webpage(s) | http://hunch.net/~jl/projects/interactive/sidebandits/bandit.pdf |
| Alternate Webpage(s) | http://papers.nips.cc/paper/3178-the-epoch-greedy-algorithm-for-multi-armed-bandits-with-side-information.pdf |
| Alternate Webpage(s) | http://books.nips.cc/papers/files/nips20/NIPS2007_0785.pdf |
| Alternate Webpage(s) | http://cseweb.ucsd.edu/~kamalika/teaching/CSE291W11/feb28.pdf |
| Alternate Webpage(s) | http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2007_785.pdf |
| Journal | NIPS 2007 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
