Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
2
Overestimating test-time scaling rewards is mitigated by a novel Bayesian approach that explicitly models and corrects for both PRM and policy uncertainties.
Offline risk-sensitive RL is now provably efficient, with new algorithms and tight bounds for dynamic and static optimized certainty equivalents.