Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective

Abstract

Within the framework of Multi-Agent Reinforcement Learning, Social Learning is a new class of algorithms that enables agents to reshape the reward function of other agents with the goal of promoting cooperation and achieving higher global rewards in mixed-motive games. However, this new modification allows agents unprecedented access to each other's learning process, which can drastically increase the risk of manipulation when an agent does not realize it is being deceived into adopting policies which are not actually in its own best interest. This research review introduces the problem statement, defines key concepts, critically evaluates existing evidence and addresses open problems that should be addressed in future research.

References in corpus (22)

• Playing Atari with Deep Reinforcement Learning
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Solving Rubik's Cube with a Robot Hand
• Deep Reinforcement Learning for Cyber Security
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
• A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity
• Reinforcement Learning for Solving the Vehicle Routing Problem
• Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning
• SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
• A multi-agent reinforcement learning model of common-pool resource appropriation
• The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
• Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
• "Other-Play" for Zero-Shot Coordination
• On Learning Intrinsic Rewards for Policy Gradient Methods
• Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances
• Open Problems in Cooperative AI
• On the Robustness of Cooperative Multi-Agent Reinforcement Learning
• Leveraging Human Guidance for Deep Reinforcement Learning Tasks
• Multi-Agent Reinforcement Learning for Unmanned Aerial Vehicle Coordination by Multi-Critic Policy Gradient Optimization
• Learning Complex Multi-Agent Policies in Presence of an Adversary
• Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo Loss