Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement Learning

TL;DR

This paper introduces a novel approach combining belief space planning, adversary modeling, and maximum entropy reinforcement learning to enhance active perception robustness against adversarial behaviors in autonomous agents.

Contribution

It presents a new stochastic belief space policy framework that accounts for adversarial strategies and minimizes predictability, improving robustness over standard methods.

Findings

Policy outperforms standard POMDP approaches against adaptive adversaries.

Incorporates adversary modeling into belief space planning.

Demonstrates increased robustness in simulated adversarial scenarios.

Abstract

We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further evidence to help discriminate potential threats. The main technical challenges are the partial observability of the agent intent, the adversary modeling, and the corresponding uncertainty modeling. Note that an adversary agent may act to mislead the autonomous agent by using a deceptive strategy that is learned from past experiences. We propose an approach that combines belief space planning, generative adversary modeling, and maximum entropy reinforcement learning to obtain a stochastic belief space policy. By accounting for various adversarial behaviors in the simulation framework and minimizing the predictability of the autonomous agent's action, the resulting policy is more robust to unmodeled adversarial strategies. This improved robustness is empirically shown against an adversary that adapts to and exploits the autonomous agent's policy when compared with a standard Chance-Constraint Partially Observable Markov Decision Process robust approach.