PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas

TL;DR

This paper introduces PIMbot, a novel method for manipulating reward functions in multi-robot reinforcement learning to influence cooperation outcomes, with experimental validation in simulated environments.

Contribution

The paper proposes a new approach, PIMbot, for policy and incentive manipulation in multi-robot RL, revealing how communication can be exploited to alter social dilemma outcomes.

Findings

PIMbot can accelerate convergence to optimal cooperation.

Manipulation can improve or impair task performance.

Experimental results validate effectiveness in simulated environments.

Abstract

Recent research has demonstrated the potential of reinforcement learning (RL) in enabling effective multi-robot collaboration, particularly in social dilemmas where robots face a trade-off between self-interests and collective benefits. However, environmental factors such as miscommunication and adversarial robots can impact cooperation, making it crucial to explore how multi-robot communication can be manipulated to achieve different outcomes. This paper presents a novel approach, namely PIMbot, to manipulating the reward function in multi-robot collaboration through two distinct forms of manipulation: policy and incentive manipulation. Our work introduces a new angle for manipulation in recent multi-agent RL social dilemmas that utilize a unique reward function for incentivization. By utilizing our proposed PIMbot mechanisms, a robot is able to manipulate the social dilemma environment effectively. PIMbot has the potential for both positive and negative impacts on the task outcome, where positive impacts lead to faster convergence to the global optimum and maximized rewards for any chosen robot. Conversely, negative impacts can have a detrimental effect on the overall task performance. We present comprehensive experimental results that demonstrate the effectiveness of our proposed methods in the Gazebo-simulated multi-robot environment. Our work provides insights into how inter-robot communication can be manipulated and has implications for various robotic applications. %, including robotics, transportation, and manufacturing.