Open Problems in Cooperative AI
- URL: http://arxiv.org/abs/2012.08630v1
- Date: Tue, 15 Dec 2020 21:39:50 GMT
- Title: Open Problems in Cooperative AI
- Authors: Allan Dafoe and Edward Hughes and Yoram Bachrach and Tantum Collins
and Kevin R. McKee and Joel Z. Leibo and Kate Larson and Thore Graepel
- Abstract summary: Research aims to study the many aspects of the problems of cooperation and to innovate in AI to contribute to solving these problems.
This research integrates ongoing work on multi-agent systems, game theory and social choice, human-machine interaction and alignment, natural-language processing, and the construction of social tools and platforms.
- Score: 21.303564222227727
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Problems of cooperation--in which agents seek ways to jointly improve their
welfare--are ubiquitous and important. They can be found at scales ranging from
our daily routines--such as driving on highways, scheduling meetings, and
working collaboratively--to our global challenges--such as peace, commerce, and
pandemic preparedness. Arguably, the success of the human species is rooted in
our ability to cooperate. Since machines powered by artificial intelligence are
playing an ever greater role in our lives, it will be important to equip them
with the capabilities necessary to cooperate and to foster cooperation.
We see an opportunity for the field of artificial intelligence to explicitly
focus effort on this class of problems, which we term Cooperative AI. The
objective of this research would be to study the many aspects of the problems
of cooperation and to innovate in AI to contribute to solving these problems.
Central goals include building machine agents with the capabilities needed for
cooperation, building tools to foster cooperation in populations of (machine
and/or human) agents, and otherwise conducting AI research for insight relevant
to problems of cooperation. This research integrates ongoing work on
multi-agent systems, game theory and social choice, human-machine interaction
and alignment, natural-language processing, and the construction of social
tools and platforms. However, Cooperative AI is not the union of these existing
areas, but rather an independent bet about the productivity of specific kinds
of conversations that involve these and other areas. We see opportunity to more
explicitly focus on the problem of cooperation, to construct unified theory and
vocabulary, and to build bridges with adjacent communities working on
cooperation, including in the natural, social, and behavioural sciences.
Related papers
- Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions [67.60397632819202]
Building socially-intelligent AI agents (Social-AI) is a multidisciplinary, multimodal research goal.
We identify a set of underlying technical challenges and open questions for researchers across computing communities to advance Social-AI.
arXiv Detail & Related papers (2024-04-17T02:57:42Z) - Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social
Dilemmas [16.726750952782172]
The study of cooperation within social dilemmas has long been a fundamental topic across various disciplines.
Recent advancements in Artificial Intelligence have significantly reshaped this field.
This survey examines three key areas at the intersection of AI and cooperation in social dilemmas.
arXiv Detail & Related papers (2024-02-27T07:31:30Z) - Human AI Collaboration in Software Engineering: Lessons Learned from a
Hands On Workshop [1.14603174659129]
The study identifies key themes such as the evolving nature of human AI interaction, the capabilities of AI in software engineering tasks, and the challenges and limitations of integrating AI in this domain.
The findings show that while AI, particularly ChatGPT, improves the efficiency of code generation and optimization, human oversight remains crucial, especially in areas requiring complex problem solving and security considerations.
arXiv Detail & Related papers (2023-12-17T06:31:05Z) - SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents [107.4138224020773]
We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and humans.
In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals.
We find that GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills.
arXiv Detail & Related papers (2023-10-18T02:27:01Z) - CAMEL: Communicative Agents for "Mind" Exploration of Large Language
Model Society [58.04479313658851]
This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents.
We propose a novel communicative agent framework named role-playing.
Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems.
arXiv Detail & Related papers (2023-03-31T01:09:00Z) - The art of compensation: how hybrid teams solve collective risk dilemmas [6.081979963786028]
We study the evolutionary dynamics of cooperation in a hybrid population made of both adaptive and fixed-behavior agents.
We show how the first learn to adapt their behavior to compensate for the behavior of the latter.
arXiv Detail & Related papers (2022-05-13T13:23:42Z) - Adversarial Attacks in Cooperative AI [0.0]
Single-agent reinforcement learning algorithms in a multi-agent environment are inadequate for fostering cooperation.
Recent work in adversarial machine learning shows that models can be easily deceived into making incorrect decisions.
Cooperative AI might introduce new weaknesses not investigated in previous machine learning research.
arXiv Detail & Related papers (2021-11-29T07:34:12Z) - The Road to a Successful HRI: AI, Trust and ethicS-TRAITS [65.60507052509406]
The aim of this workshop is to give researchers from academia and industry the possibility to discuss the inter-and multi-disciplinary nature of the relationships between people and robots.
arXiv Detail & Related papers (2021-03-23T16:52:12Z) - Artificial Intelligence & Cooperation [38.19500588776648]
The rise of Artificial Intelligence will bring with it an ever-increasing willingness to cede decision-making to machines.
But rather than just giving machines the power to make decisions that affect us, we need ways to work cooperatively with AI systems.
With success, cooperation between humans and AIs can build society just as human-human cooperation has.
arXiv Detail & Related papers (2020-12-10T23:54:31Z) - Watch-And-Help: A Challenge for Social Perception and Human-AI
Collaboration [116.28433607265573]
We introduce Watch-And-Help (WAH), a challenge for testing social intelligence in AI agents.
In WAH, an AI agent needs to help a human-like agent perform a complex household task efficiently.
We build VirtualHome-Social, a multi-agent household environment, and provide a benchmark including both planning and learning based baselines.
arXiv Detail & Related papers (2020-10-19T21:48:31Z) - Joint Mind Modeling for Explanation Generation in Complex Human-Robot
Collaborative Tasks [83.37025218216888]
We propose a novel explainable AI (XAI) framework for achieving human-like communication in human-robot collaborations.
The robot builds a hierarchical mind model of the human user and generates explanations of its own mind as a form of communications.
Results show that the generated explanations of our approach significantly improves the collaboration performance and user perception of the robot.
arXiv Detail & Related papers (2020-07-24T23:35:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.