Skip to content
conftrace_

reward exploitation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

unsupervised exploration (1) reward model (1) preference feedback (1) human feedback (1) interactive reinforcement learning (1) off-policy learning (1) unsupervised pretraining (1) reward modeling (1)

Papers

PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training ICML 2021