图 书 馆
减少模仿学习和结构化预测的没遗憾的在线学习A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning |
|
| 课程网址: | http://videolectures.net/aistats2011_ross_reduction/ |
| 主讲教师: | Stephane Ross |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2011-05-06 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and often in practice. Some recent approaches (Daumé III et al., 2009; Ross and Bagnell, 2010) provide stronger guarantees in this setting, but remain somewhat unsatisfactory as they train either non-stationary or stochastic policies and require a large number of iterations. In this paper, we propose a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting. We show that any such no regret algorithm, combined with additional reduction assumptions, must find a policy with good performance under the distribution of observations it induces in such sequential settings. We demonstrate that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem. |
| 关 键 词: | 模仿学习; 结构化预测 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-09-24：dingaq |
| 阅读次数: | 82 |