@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{siddhant_agarwal_psm,
  author   = {Siddhant Agarwal and Harshit Sikchi and Peter Stone and Amy Zhang},
  title    = {Proto Successor Measure: Representing the Behavior Space of an RL Agent},
  booktitle = {International Conference on Machine Learning},
  year     = {2025},
  month    = {June},
  location = {Vancouver, Canada},
  abstract = {Having explored an environment, intelligent agents should be able to transfer
their knowledge to most downstream tasks within that environment without
additional interactions. Referred to as "zero-shot learning", this ability
remains elusive for general-purpose reinforcement learning algorithms. While
recent works have attempted to produce zero-shot RL agents, they make assumptions
about the nature of the tasks or the structure of the MDP. We present Proto
Successor Measure: the basis set for all possible behaviors of a Reinforcement
Learning Agent in a dynamical system. We prove that any possible behavior
(represented using visitation distributions) can be represented using an affine
combination of these policy-independent basis functions. Given a reward function
at test time, we simply need to find the right set of linear weights to combine
these bases corresponding to the optimal policy. We derive a practical algorithm
to learn these basis functions using reward-free interaction data from the
environment and show that our approach can produce the near-optimal policy at
test time for any given reward function without additional environmental
interactions.
  },
}