Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.02243 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929356760154112 |
|---|---|
| author | Qi, Carl Sun, Edward Zhang, Harry |
| author_facet | Qi, Carl Sun, Edward Zhang, Harry |
| contents | Behavioral cloning, or more broadly, learning from demonstrations (LfD) is a priomising direction for robot policy learning in complex scenarios. Albeit being straightforward to implement and data-efficient, behavioral cloning has its own drawbacks, limiting its efficacy in real robot setups. In this work, we take one step towards improving learning from demonstration algorithms by leveraging implicit energy-based policy models. Results suggest that in selected complex robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used neural network-based explicit models, especially in the cases of approximating potentially discontinuous and multimodal functions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02243 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Improving Learning from Demonstration Algorithms via MCMC Methods Qi, Carl Sun, Edward Zhang, Harry Robotics Behavioral cloning, or more broadly, learning from demonstrations (LfD) is a priomising direction for robot policy learning in complex scenarios. Albeit being straightforward to implement and data-efficient, behavioral cloning has its own drawbacks, limiting its efficacy in real robot setups. In this work, we take one step towards improving learning from demonstration algorithms by leveraging implicit energy-based policy models. Results suggest that in selected complex robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used neural network-based explicit models, especially in the cases of approximating potentially discontinuous and multimodal functions. |
| title | Towards Improving Learning from Demonstration Algorithms via MCMC Methods |
| topic | Robotics |
| url | https://arxiv.org/abs/2405.02243 |