English

Scaling Goal-based Exploration via Pruning Proto-goals

Machine Learning 2023-02-10 v1 Artificial Intelligence

Abstract

One of the gnarliest challenges in reinforcement learning (RL) is exploration that scales to vast domains, where novelty-, or coverage-seeking behaviour falls short. Goal-directed, purposeful behaviours are able to overcome this, but rely on a good goal space. The core challenge in goal discovery is finding the right balance between generality (not hand-crafted) and tractability (useful, not too many). Our approach explicitly seeks the middle ground, enabling the human designer to specify a vast but meaningful proto-goal space, and an autonomous discovery process to refine this to a narrower space of controllable, reachable, novel, and relevant goals. The effectiveness of goal-conditioned exploration with the latter is then demonstrated in three challenging environments.

Keywords

Cite

@article{arxiv.2302.04693,
  title  = {Scaling Goal-based Exploration via Pruning Proto-goals},
  author = {Akhil Bagaria and Ray Jiang and Ramana Kumar and Tom Schaul},
  journal= {arXiv preprint arXiv:2302.04693},
  year   = {2023}
}
R2 v1 2026-06-28T08:35:58.547Z