Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL
arxiv(2023)
摘要
Reinforcement learning agents tend to develop habits that are effective only
under specific policies. Following an initial exploration phase where agents
try out different actions, they eventually converge onto a particular policy.
As this occurs, the distribution over state-action trajectories becomes
narrower, leading agents to repeatedly experience the same transitions. This
repetitive exposure fosters spurious correlations between certain observations
and rewards. Agents may then pick up on these correlations and develop
simplistic habits tailored to the specific set of trajectories dictated by
their policy. The problem is that these habits may yield incorrect outcomes
when agents are forced to deviate from their typical trajectories, prompted by
changes in the environment. This paper presents a mathematical characterization
of this phenomenon, termed policy confounding, and illustrates, through a
series of examples, the circumstances under which it occurs.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要