Name
Abstract | ||
|---|---|---|
Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system to learn controllers, which is a practical limitation in real systems, such as robots, where many interactions can be impractical and time consuming. To address this problem, current learning approaches typically require task-specific knowledge in form of expert demonstrations, realistic simulators, pre-shaped policies, or specific knowledge about the underlying dynamics. In this paper, we follow a different approach and speed up learning by extracting more information from data. In particular, we learn a probabilistic, non-parametric Gaussian process transition model of the system. By explicitly incorporating model uncertainty into long-term planning and controller learning our approach reduces the effects of model errors, a key problem in model-based learning. Compared to state-of-the art RL our model-based policy search method achieves an unprecedented speed of learning. We demonstrate its applicability to autonomous learning in real robot and control tasks. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/TPAMI.2013.218 | Pattern Analysis and Machine Intelligence, IEEE Transactions |
Keywords | DocType | Volume |
bayesian inference,gaussian processes,policy search,control,reinforcement learning,robotics,predictive models,computational modeling,data models,probabilistic logic,robots,uncertainty | Journal | 37 |
Issue | ISSN | Citations |
2 | 0162-8828 | 101 |
PageRank | References | Authors |
3.62 | 34 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marc Peter Deisenroth | 1 | 1095 | 64.71 |
| Dieter Fox | 2 | 12306 | 1289.74 |
| carl edward rasmussen | 3 | 2628 | 309.77 |