$\pi2\text{vec}$: Policy Representations with Successor Features

Autor:	Scarpellini, Gianluca, Konyushkova, Ksenia, Fantacci, Claudio, Paine, Tom Le, Chen, Yutian, Denil, Misha
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted paper at ICLR2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.09800 Zobrazit plný text záznamu View this record from Arxiv