BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

arXiv:2210.04688v5 Announce Type: replace-cross
Abstract: Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL paradigm because it saves the interactions with environments. In offline RL, data providers share large pre-collected datasets, and others can train high-quality agents without interacting with the environments. This paradigm has demonstrated effectiveness in critical tasks like robot control, autonomous driving, etc. However, less attention is paid to investigating the …

agent arxiv backdoors baffle can cs.ai cs.cr cs.lg data datasets environment environments error experiences high large learn offline paradigm popular quality share train trial