conftrace_

value-function pessimism

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

critic reconstruction (1) constrained fine-tuning (1) offline-to-online reinforcement learning (1) distribution shift (1) policy optimization (1)

Papers

Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL NeurIPS 2024