Timezone: »

Cooperative AI
Natasha Jaques · Edward Hughes · Jakob Foerster · Noam Brown · Kalesha Bullard · Charlotte Smith

Tue Dec 14 05:20 AM -- 01:45 PM (PST) @ None
Event URL: https://www.cooperativeai.com/neurips-2021 »

The human ability to cooperate in a wide range of contexts is a key ingredient in the success of our species. Problems of cooperation—in which agents seek ways to jointly improve their welfare—are ubiquitous and important. They can be found at every scale, from the daily routines of highway driving, communicating in shared language and work collaborations, to the global challenges of climate change, pandemic preparedness and international trade. With AI agents playing an ever greater role in our lives, we must endow them with similar abilities. In particular they must understand the behaviors of others, find common ground by which to communicate with them, make credible commitments, and establish institutions which promote cooperative behavior. By construction, the goal of Cooperative AI is interdisciplinary in nature. Therefore, our workshop will bring together scholars from diverse backgrounds including reinforcement learning (and inverse RL), multi-agent systems, human-AI interaction, game theory, mechanism design, social choice, fairness, cognitive science, language learning, and interpretability. This year we will organize the workshop along two axes. First, we will discuss how to incentivize cooperation in AI systems, developing algorithms that can act effectively in general-sum settings, and which encourage others to cooperate. The second focus is on how to implement effective coordination, given that cooperation is already incentivized. For example, we may examine zero-shot coordination, in which AI agents need to coordinate with novel partners at test time. This setting is highly relevant to human-AI coordination, and provides a stepping stone for the community towards full Cooperative AI.

Tue 5:20 a.m. - 5:30 a.m.
Welcome and Opening Remarks
Edward Hughes, Natasha Jaques
Tue 5:30 a.m. - 6:00 a.m.
Invited Talk: Bo An (Nanyang Technological University) on Learning to Coordinate in Complex Environments (Invited Talk)
Bo An
Tue 6:00 a.m. - 6:30 a.m.

In the modern world, we cooperate with and live side by side with strangers, who often look, act, and speak in ways very different to us. We work together on goals with culturally distant nations that span the globe. I'm recording this talk, but I could have given it to you in person. That's unusual in many respects. It's unusual from a cross-species perspective - comparing us to our closest primate cousins, a room full of strange chimps is a room full of dead chimps. It's unusual from a historical perspective - even a few hundred years ago, a stranger in our midst was a potential threat. And it's unusual from a geographic perspective - even today some places are safer and more cooperative than others. Cooperation varies in scale, intensity, and domain - some countries cooperate on healthcare, others on defence. Compounding the puzzle, the evolutionary mechanisms that explain cooperation undermine one another and can stabilize non-cooperative or even maladaptive behavior. I'll discuss the latest discoveries in the science of cultural evolution and human cooperation and how these might apply to the development of cooperative AI.

Michael Muthukrishna
Tue 6:30 a.m. - 7:00 a.m.

In this talk I will present some of our findings (in collaboration with the Bank of Canada) on using RL to approximate the policy rules of banks participating in a high-value payments system. The objective of the agents is to learn a policy function for the choice of amount of liquidity provided to the system at the beginning of the day. Individual choices have complex strategic effects precluding a closed form solution of the optimal policy, except in simple cases. We show that in a simplified two-agent setting, agents using reinforcement learning do learn the optimal policy that minimizes the cost of processing their individual payments. We also show that in more complex settings, both agents learn to reduce their liquidity costs. Our results show the applicability of RL to estimate best-response functions in real-world strategic games.

Pablo Samuel Castro
Tue 7:00 a.m. - 7:15 a.m.
Q&A with Invited Speaker (1) (Live Q&A)
Tue 7:15 a.m. - 7:30 a.m.
Q&A with Invited Speaker (2) (Live Q&A)
Tue 7:30 a.m. - 7:45 a.m.
Q&A with Invited Speaker (3) (Live Q&A)
Tue 7:45 a.m. - 8:15 a.m.

Sortition is a storied paradigm of democracy built on the idea of choosing representatives through lotteries instead of elections. In recent years this idea has found renewed popularity in the form of citizens’ assemblies, which bring together randomly selected people from all walks of life to discuss key questions and deliver policy recommendations. A principled approach to sortition, however, must resolve the tension between two competing requirements: that the demographic composition of citizens’ assemblies reflect the general population and that every person be given a fair chance (literally) to participate. I will describe our work on designing, analyzing and implementing randomized participant selection algorithms that balance these two requirements. I will also discuss practical challenges in sortition based on experience with the adoption and deployment of our open-source system, Panelot.

Ariel Procaccia
Tue 8:15 a.m. - 8:45 a.m.

Today I will be talking about the role of conventions in human-AI collaboration. Conventions are norms/equilibria we build through repeated interactions with each other. The idea of conventions has been well-studied in linguistics. We will start the talk by discussing the notion of linguistic conventions, and how we can build AI agents that can effectively build these conventions. We then extend the idea of linguistic conventions to conventions through actions. We discuss a modular approach to separate partner-specific conventions and rule-dependent representations. We then discuss how this can be done effectively when working with partners whose actions are high dimensional. Finally we extend the notion of conventions to larger scale systems beyond dyadic interactions. Specifically, we discuss what conventions/equilibria emerge in mixed-autonomy traffic networks and how that can be leveraged for better dynamic routing of vehicles.

Dorsa Sadigh
Tue 8:45 a.m. - 9:15 a.m.
Invited Talk: Nika Haghtalab (UC Berkeley) (Invited Talk)
Nika Haghtalab
Tue 9:15 a.m. - 9:30 a.m.
Q&A with Invited Speaker (4) (Live Q&A)
Tue 9:30 a.m. - 9:45 a.m.
Q&A with Invited Speaker (5) (Live Q&A)
Tue 9:45 a.m. - 10:00 a.m.
Q&A with Invited Speaker (6) (Live Q&A)
Tue 10:00 a.m. - 11:30 a.m.
Workshop Poster Sessions (hosted in GatherTown) (Poster Sessions (GatherTown))
Tue 11:30 a.m. - 12:30 p.m.
(Live) Panel Discussion: Cooperative AI (Panel Discussion)
Kalesha Bullard, Allan Dafoe, Fei Fang, Chris Amato, Elizabeth Adams
Tue 12:30 p.m. - 12:45 p.m.
Spotlight Talk 1 (Spotlight Talk)
Charlotte Smith
Tue 12:45 p.m. - 1:00 p.m.
Spotlight Talk 2 (Spotlight Talk)
Charlotte Smith
Tue 1:00 p.m. - 1:15 p.m.
Spotlight Talk 3 (Spotlight Talk)
Charlotte Smith
Tue 1:15 p.m. - 1:30 p.m.
Spotlight Talk 4 (Spotlight Talk)
Charlotte Smith
Tue 1:30 p.m. - 1:45 p.m.
Closing Remarks
Gillian Hadfield

Author Information

Natasha Jaques (UC Berkeley)
Edward Hughes (DeepMind)
Jakob Foerster (Facebook AI Research)

Jakob Foerster received a CIFAR AI chair in 2019 and is starting as an Assistant Professor at the University of Toronto and the Vector Institute in the academic year 20/21. During his PhD at the University of Oxford, he helped bring deep multi-agent reinforcement learning to the forefront of AI research and interned at Google Brain, OpenAI, and DeepMind. He has since been working as a research scientist at Facebook AI Research in California, where he will continue advancing the field up to his move to Toronto. He was the lead organizer of the first Emergent Communication (EmeCom) workshop at NeurIPS in 2017, which he has helped organize ever since.

Noam Brown (Carnegie Mellon University)
Kalesha Bullard (Facebook AI Research)
Charlotte Smith (DeepMind)

More from the Same Authors