An Attention Mechanism for Deep Q-Networks with Applications in Robotic Pushing
| Type of publication: | Idiap-RR |
| Citation: | Ewerton_Idiap-RR-03-2021 |
| Number: | Idiap-RR-03-2021 |
| Year: | 2021 |
| Month: | 4 |
| Institution: | Idiap |
| Abstract: | Humans effortlessly solve push tasks in everyday life but unlocking these capabilities remains a research challenge in robotics. Physical models are often inaccurate or unattainable. State-of-the-art data-driven approaches learn to compensate for these inaccuracies or get rid of the approximated physical models altogether. Nevertheless, data-driven approaches such as Deep Q-Networks (DQNs) get frequently stuck in local optima in large state-action spaces. We propose an attention mechanism for DQNs to improve their sampling efficiency and demonstrate in simulation experiments with a UR5 robot arm that such a mechanism helps the DQN learn faster and achieve higher performance in a push task involving objects with unknown dynamics. |
| Keywords: | |
| Projects |
Idiap |
| Authors | |
| Crossref by |
Ewerton_ICRAW_2021 |
| Added by: | [ADM] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
