Deceptive Kernel Function on Observations of Discrete POMDP

TL;DR

This paper introduces a deceptive kernel function for observations in discrete POMDPs, demonstrating how it can mislead the agent's belief and significantly reduce its rewards through theoretical analysis and experiments.

Contribution

It presents a novel deceptive kernel function applied to POMDP observations and analyzes its impact on agent belief and performance using multiple algorithms.

Findings

Deceptive kernel can mislead agent's belief and reduce rewards

Certain kernel implementations induce abnormal agent behaviors

Experimental results confirm the detrimental effects of the deception

Abstract

This paper studies the deception applied on agent in a partially observable Markov decision process. We introduce deceptive kernel function (the kernel) applied to agent's observations in a discrete POMDP. Based on value iteration, value function approximation and POMCP three characteristic algorithms used by agent, we analyze its belief being misled by falsified observations as the kernel's outputs and anticipate its probable threat on agent's reward and potentially other performance. We validate our expectation and explore more detrimental effects of the deception by experimenting on two POMDP problems. The result shows that the kernel applied on agent's observation can affect its belief and substantially lower its resulting rewards; meantime certain implementation of the kernel could induce other abnormal behaviors by the agent.