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.
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 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
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.