English

Diversity Progress for Goal Selection in Discriminability-Motivated RL

Artificial Intelligence 2024-11-07 v2 Machine Learning

Abstract

Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: "Diversity Progress" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward can motivate the agent to learn a set of diverse skills without extrinsic rewards. We demonstrate empirically that a DP-motivated agent can learn a set of distinguishable skills faster than previous approaches, and do so without suffering from a collapse of the goal distribution -- a known issue with some prior approaches. We end with plans to take this proof-of-concept forward.

Keywords

Cite

@article{arxiv.2411.01521,
  title  = {Diversity Progress for Goal Selection in Discriminability-Motivated RL},
  author = {Erik M. Lintunen and Nadia M. Ady and Christian Guckelsberger},
  journal= {arXiv preprint arXiv:2411.01521},
  year   = {2024}
}

Comments

11 pages including appendices, full-track paper at the Intrinsically Motivated Open-ended Learning workshop at NeurIPS 2024

R2 v1 2026-06-28T19:46:24.152Z