Multiarmed Bandits and Partial Monitoring Exploration and Exploitation using Upper Confidence Bounds
author:
Nicolò Cesa-Bianchi,
Università degli Studi di Milano
You might be experiencing some problems with Your Video player.
| Slides | |
| 0:00 | MULTIARMED BANDITS |
| 1:36 | THE BANDIT PROBLEM |
| 5:07 | FINITE-TIME REGRET |
| 13:02 | HORIZON-DEPENDENT REWARD DISTRIBUTIONS |
| 16:55 | HORIZON-DEP. REWARD DISTRIBUTIONS (CONT.) |
| 22:21 | THE NONSTOCHASTIC BANDIT PROBLEM |
| 27:12 | THE NONSTOCHASTIC BANDIT PROBLEM |
| 29:33 | A NEARLY OPTIMAL RANDOMIZED POLICY |
| 30:15 | THE NONSTOCHASTIC BANDIT PROBLEM |
| 31:00 | A NEARLY OPTIMAL RANDOMIZED POLICY |
| 37:42 | PROOF 1/2 |
| 39:16 | A NEARLY OPTIMAL RANDOMIZED POLICY |
| 39:20 | PROOF 1/2 |
| 39:35 | PROOF 2/2 |
| 39:41 | PROOF 1/2 |
| 39:47 | PROOF 2/2 |
| 40:15 | A NEARLY OPTIMAL RANDOMIZED POLICY |
| 40:21 | PROOF 2/2 |
| 40:56 | A NEARLY OPTIMAL RANDOMIZED POLICY |
| 41:18 | PROOF 2/2 |
| 42:03 | PROOF 1/2 |
| 42:05 | A POINTWISE BOUND |
| 43:20 | REGRET BOUNDS |
| 47:12 | VARIANCE PROBLEM |
| 47:23 | REGRET BOUNDS |
| 47:28 | VARIANCE PROBLEM |
| 48:17 | REGRET BOUNDS THAT HOLD W.H.P. |
| 49:43 | COMPETING AGAINST ARBITRARY POLICIES |
| 51:33 | TRACKING REGRET |
| 51:51 | A BOUND ON THE TRACKING REGRET |
| 57:48 | PARTIAL MONITORING |
| 57:53 | FORECASTING A SEQUENCE |
| 60:25 | PREDICTION WITH EXPERT ADVICE |
| 61:20 | MULTIARMED BANDIT |
| 62:23 | PARTIAL MONITORING |
| 64:12 | EXAMPLES: APPLE TASTING |
| 66:26 | EXAMPLES: LABEL EFFICIENT FORECASTING |
| 67:53 | EXAMPLES: DYNAMIC PRICING |
| 70:23 | CONTROLLING THE REGRET |
| 72:55 | THE GENERAL FORECASTER FOR PARTIAL MONITORING |
| 73:10 | CONTROLLING THE REGRET |
| 73:16 | REGRET BOUNDS |
| 74:03 | LOWER BOUNDS |
| 74:24 | EXAMPLES: APPLE TASTING |
| 74:38 | EXAMPLES: LABEL EFFICIENT FORECASTING |
| 74:47 | EXAMPLES: DYNAMIC PRICING |
| 75:44 | EXAMPLES: LABEL EFFICIENT FORECASTING |
| 77:01 | CONTROLLING THE REGRET |
| 77:24 | LOWER BOUNDS |
| 78:14 | A STRATEGY FOR REVEALING ACTIONS |
Lecture rating
| People found this lecture: | ||
| Worth seeing | ||
| because it is: | ||
| Valuable and informative | ||
| Well presented | ||
| Easily understandable | ||
| Acceptably recorded | ||
| You need to login to cast your vote. | ||
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Related content
2 comments
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !
