arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.15019cs.LGcs.CR
收藏

基于互信息正则化策略梯度的隐私约束策略

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

Stanford University(斯坦福大学)

Chris Cundy, Rishi Desai, Stefano Ermon

AI总结:

本文提出在策略梯度框架中引入互信息正则化器,在最大化奖励的同时最小化动作对敏感状态的披露,并开发了基于模型和无模型的优化估计器,实验证明其在高维任务中能有效隐藏敏感状态。

摘要:

随着强化学习技术越来越多地应用于现实世界的决策问题,人们开始关注这些算法如何使用潜在的敏感信息。我们考虑训练一个策略的任务,该策略在最大化奖励的同时,通过动作最小化对某些敏感状态变量的披露。我们举例说明这一设定如何涵盖顺序决策中的现实世界隐私问题。我们在策略梯度框架中通过引入一个基于敏感状态与动作之间互信息(MI)的正则化器来解决该问题。我们开发了一个基于模型的随机梯度估计器,用于优化隐私约束策略。我们还讨论了另一种替代的MI正则化器,它作为我们主要MI正则化器的上界,并且可以在无模型环境中进行优化,以及一种强大的直接估计器,可用于具有可微动力学的环境。我们将先前差分隐私强化学习的工作与我们的互信息信息披露公式进行了对比。实验结果表明,我们的训练方法能够产生隐藏敏感状态的策略,即使在具有挑战性的高维任务中也是如此。

英文摘要:

As reinforcement learning techniques are increasingly applied to real-world decision problems, attention has turned to how these algorithms use potentially sensitive information. We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions. We give examples of how this setting covers real-world problems in privacy for sequential decision-making. We solve this problem in the policy gradients framework by introducing a regularizer based on the mutual information (MI) between the sensitive state and the actions. We develop a model-based stochastic gradient estimator for optimization of privacy-constrained policies. We also discuss an alternative MI regularizer that serves as an upper bound to our main MI regularizer and can be optimized in a model-free setting, and a powerful direct estimator that can be used in an environment with differentiable dynamics. We contrast previous work in differentially-private RL to our mutual-information formulation of information disclosure. Experimental results show that our training method results in policies that hide the sensitive state, even in challenging high-dimensional tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑