pith. sign in

Deep reinforcement learning from human preferences.Advances in neural information process- ing systems, 30

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking

cs.LG · 2026-04-29 · unverdicted · novelty 5.0

UARD is a reinforcement learning method that discounts rewards using combined epistemic and aleatoric uncertainty signals via a Reliability Filter, with claimed convergence guarantees and large reductions in reward hacking on benchmarks.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking cs.LG · 2026-04-29 · unverdicted · none · ref 3

    UARD is a reinforcement learning method that discounts rewards using combined epistemic and aleatoric uncertainty signals via a Reliability Filter, with claimed convergence guarantees and large reductions in reward hacking on benchmarks.