Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks

2024-02-09 · Michael Y. Fatemi, Wesley A. Suttle, Brian M. Sadler

Deceptive path planning (DPP) is the problem of designing a path that hides its true goal from an outside observer. Existing methods for DPP rely on unrealistic assumptions, such as global state observability and perfect model knowledge, and are typically problem-specific, meaning that even minor changes to a previously solved problem can force expensive computation of an entirely new solution. Given these drawbacks, such methods do not generalize to unseen problem instances, lack scalability to realistic problem sizes, and preclude both on-the-fly tunability of deception levels and real-time adaptivity to changing environments. In this paper, we propose a reinforcement learning (RL)-based scheme for training policies to perform DPP over arbitrary weighted graphs that overcomes these issues. The core of our approach is the introduction of a local perception model for the agent, a new state space representation distilling the key components of the DPP problem, the use of graph neural network-based policies to facilitate generalization and scaling, and the introduction of new deception bonuses that translate the deception objectives of classical methods to the RL setting. Through extensive experimentation we show that, without additional fine-tuning, at test time the resulting policies successfully generalize, scale, enjoy tunable levels of deception, and adapt in real-time to changes in the environment.

📄 PDF Abstract BibTeX arXiv:2402.06552

Code (1)

myfatemi04/rl-deceptive-graph-planning 공식 구현 pytorch

Tasks

Graph Neural Network reinforcement-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)

Value of Information-based Deceptive Path Planning Under Adversarial Interventions

2025-03-31 · Wesley A. Suttle, Jesse Milzman, Mustafa O. Karabag, Brian M. Sadler 외

Existing methods for deceptive path planning (DPP) address the problem of designing paths that conceal their true goal from a passive, external observer. Such methods do not apply to problems where the observer has the a…

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 …

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)

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 exp…

Privacy Preserving reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)