Certain errors in proxy rewards for policy gradient methods can be benign or beneficial by preventing policies from stalling on outputs with mediocre ground truth rewards, enabling improved RLHF metrics and reward design insights.
On the theory of policy gradient methods: Optimality, approximation, and distribution shift.The Journal of Machine Learning Research, 22(1):4431–4506
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
-
When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient
Certain errors in proxy rewards for policy gradient methods can be benign or beneficial by preventing policies from stalling on outputs with mediocre ground truth rewards, enabling improved RLHF metrics and reward design insights.