Skip to content
conftrace_

reward augmentation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dynamics shift (1) offline dataset (1) reward augmented (1) adaptive policy (1) training stability (1) model-free reinforcement learning (1) generative adversarial network (1) maximum likelihood estimation (1) maximum likelihood (1) adversarial training (1)

Papers

DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning ICLR 2022 ARAML: A Stable Adversarial Training Framework for Text Generation EMNLP 2019