图 书 馆
学习机器人世界杯足球锦标赛方法的要点Learning RoboCup-Keepaway with Kernels |
|
| 课程网址: | http://videolectures.net/gpip06_jung_lrkk/ |
| 主讲教师: | Tobias Jung |
| 开课单位: | 德克萨斯大学 |
| 开课时间: | 2007-02-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We give another success story of using kernel-based methods to solve a dificult reinforcement learning problem, namely that of 3vs2 keepaway in RoboCup simulated soccer. Key challenges in keepaway are the high-dimensionality of the state space (rendering conventional grid-based function approximation like tilecoding infeasable) and the stochasticity due to noise and multiple learning agents needing to co- operate. We use approximate policy iteration with sparsified regular- ization networks to carry out policy evaluation. Preliminary results indicate that the behavior learned through our approach clearly out- performs the best results obtained with tilecoding by Stone et al. |
| 关 键 词: | 强化学习问题; 高维状态空间; 近似策略 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-08：yumf |
| 阅读次数: | 41 |