Cooperating with Machines

Abstract

Since Alan Turing envisioned Artificial Intelligence (AI) [1], a major driving force behind technical progress has been competition with human cognition. Historical milestones have been frequently associated with computers matching or outperforming humans in difficult cognitive tasks (e.g. face recognition [2], personality classification [3], driving cars [4], or playing video games [5]), or defeating humans in strategic zero-sum encounters (e.g. Chess [6], Checkers [7], Jeopardy! [8], Poker [9], or Go [10]). In contrast, less attention has been given to developing autonomous machines that establish mutually cooperative relationships with people who may not share the machine's preferences. A main challenge has been that human cooperation does not require sheer computational power, but rather relies on intuition [11], cultural norms [12], emotions and signals [13, 14, 15, 16], and pre-evolved dispositions toward cooperation [17], common-sense mechanisms that are difficult to encode in machines for arbitrary contexts. Here, we combine a state-of-the-art machine-learning algorithm with novel mechanisms for generating and acting on signals to produce a new learning algorithm that cooperates with people and other machines at levels that rival human cooperation in a variety of two-player repeated stochastic games. This is the first general-purpose algorithm that is capable, given a description of a previously unseen game environment, of learning to cooperate with people within short timescales in scenarios previously unanticipated by algorithm designers. This is achieved without complex opponent modeling or higher-order theories of mind, thus showing that flexible, fast, and general human-machine cooperation is computationally achievable using a non-trivial, but ultimately simple, set of algorithmic mechanisms.

An updated version of this paper was published in Nature Communications

References in corpus (5)

• DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Efficient Model Learning for Human-Robot Collaborative Tasks
• Critical dynamics in the evolution of stochastic strategies for the iterated Prisoner's Dilemma
• A Polynomial-time Nash Equilibrium Algorithm for Repeated Stochastic Games

Cited by in corpus (26)

• Social physics
• A Taxonomy of Prompt Modifiers for Text-To-Image Generation
• Maintaining cooperation in complex social dilemmas using deep reinforcement learning
• AI-enhanced Collective Intelligence
• Emergent Communication through Negotiation
• Deployment and Evaluation of a Flexible Human-Robot Collaboration Model Based on AND/OR Graphs in a Manufacturing Environment
• Emergent Multi-Agent Communication in the Deep Learning Era
• Designing Deep Reinforcement Learning for Human Parameter Exploration
• Navigating the Landscape of Multiplayer Games
• Consequentialist conditional cooperation in social dilemmas with imperfect information
• Learning to Play No-Press Diplomacy with Best Response Policy Iteration
• Facilitating Cooperation in Human-Agent Hybrid Populations through Autonomous Agents
• Open Problems in Cooperative AI
• Learning enables adaptation in cooperation for multi-player stochastic games
• The Science Fiction Science Method
• Enhancing social cohesion with cooperative bots in societies of greedy, mobile individuals
• Democratizing AI: Non-expert design of prediction tasks
• Exit options sustain altruistic punishment and decrease the second-order free-riders, but it is not a panacea
• Continuous Coordination As a Realistic Scenario for Lifelong Learning
• Human-agent coordination in a group formation game
• Group formation on a small-world: experiment and modelling
• Multi-Armed Bandits with Fairness Constraints for Distributing Resources to Human Teammates
• Multi-Agent Reinforcement Learning and Human Social Factors in Climate Change Mitigation
• Towards a Programmable Framework for Agent Game Playing
• Scientists in silico?
• Towards an Interface Description Template for AI-enabled Systems