Deceptive Reinforcement Learning for Privacy-Preserving Planning

2021-02-05 · Zhengshang Liu, Yue Yang, Tim Miller, Peta Masters

In this paper, we study the problem of deceptive reinforcement learning to preserve the privacy of a reward function. Reinforcement learning is the problem of finding a behaviour policy based on rewards received from exploratory behaviour. A key ingredient in reinforcement learning is a reward function, which determines how much reward (negative or positive) is given and when. However, in some situations, we may want to keep a reward function private; that is, to make it difficult for an observer to determine the reward function used. We define the problem of privacy-preserving reinforcement learning, and present two models for solving it. These models are based on dissimulation -- a form of deception that `hides the truth'. We evaluate our models both computationally and via human behavioural experiments. Results show that the resulting policies are indeed deceptive, and that participants can determine the true reward function less reliably than that of an honest agent.

📄 PDF Abstract BibTeX arXiv:2102.03022

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preservingreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deceptive Reinforcement Learning in Model-Free Domains

2023-03-20 · Alan Lewis, Tim Miller

This paper investigates deceptive reinforcement learning for privacy preservation in model-free and continuous action space domains. In reinforcement learning, the reward function defines the agent's objective. In advers…

model reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games

2019-08-12 · Philip Bontrager, Ahmed Khalifa, Damien Anderson, Matthew Stephenson 외

Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Cr…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Repeated Deceptive Path Planning against Learnable Observer

2026-05-08 · Shiyue Cao, Pei Xu, Likun Yang, Lei Cui 외 arxiv

We study the problem of deceptive path planning (DPP), where an agent aims to conceal its true destination from external observers. While existing work assumes static, non-learning observers, real-world adversaries-such …

Go-Explore for Residential Energy Management

2024-01-15 · Junlin Lu, Patrick Mannion, Karl Mason

Reinforcement learning is commonly applied in residential energy management, particularly for optimizing energy costs. However, RL agents often face challenges when dealing with deceptive and sparse rewards in the energy…

Efficient Exploration energy management Management reinforcement-learning+1

Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes

2021-10-19 · Chonghua Liao, Jiafan He, Quanquan Gu

Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data. To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this…

Privacy Preserving reinforcement-learning Reinforcement Learning (RL)