$\pi2\text{vec}$: Policy Representations with Successor Features
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910306282766336 |
|---|---|
| author | Scarpellini, Gianluca Konyushkova, Ksenia Fantacci, Claudio Paine, Tom Le Chen, Yutian Denil, Misha |
| author_facet | Scarpellini, Gianluca Konyushkova, Ksenia Fantacci, Claudio Paine, Tom Le Chen, Yutian Denil, Misha |
| contents | This paper describes $\pi2\text{vec}$, a method for representing behaviors of black box policies as feature vectors. The policy representations capture how the statistics of foundation model features change in response to the policy behavior in a task agnostic way, and can be trained from offline data, allowing them to be used in offline policy selection. This work provides a key piece of a recipe for fusing together three modern lines of research: Offline policy evaluation as a counterpart to offline RL, foundation models as generic and powerful state representations, and efficient policy selection in resource constrained environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_09800 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | $\pi2\text{vec}$: Policy Representations with Successor Features Scarpellini, Gianluca Konyushkova, Ksenia Fantacci, Claudio Paine, Tom Le Chen, Yutian Denil, Misha Machine Learning Robotics This paper describes $\pi2\text{vec}$, a method for representing behaviors of black box policies as feature vectors. The policy representations capture how the statistics of foundation model features change in response to the policy behavior in a task agnostic way, and can be trained from offline data, allowing them to be used in offline policy selection. This work provides a key piece of a recipe for fusing together three modern lines of research: Offline policy evaluation as a counterpart to offline RL, foundation models as generic and powerful state representations, and efficient policy selection in resource constrained environments. |
| title | $\pi2\text{vec}$: Policy Representations with Successor Features |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2306.09800 |