Skip to main content
Search

# Verifier-free Reinforcement Learning

1 related articles

Subscribe to updates
  1. arXiv

    RLCPR characterizes posterior concentration and beats a state-of-the-art verifier-free RL baseline by up to 4.0% on six of seven benchmarks

    This work identifies a length-dependent failure mode of probability-based rewards in verifier-free reinforcement learning, termed the Posterior Concentration Phenomenon (PCP), in which the probability of a reference answer conditioned on a reasoning trace collapses to a low-variance interval as the trace grows long and rewards become nearly indistinguishable, and proposes RLCPR, a framework with uncertainty-aware data sampling and concentration-aware regularization that improves optimization stability and token efficiency, outperforming the state-of-the-art verifier-free RL baseline by up to 4.0% on six of seven benchmarks.

You’re all caught up