1.1k citations · 3k across the 23 of their papers we have counts for
29 papers
Influencing Long-Term Behavior in Multiagent Reinforcement Learning
Dong-Ki Kim, Matthew Riemer, Miao Liu +5
The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behavio…
Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers
Danielle Rothermel, Margaret Li, Tim Rocktäschel +1
Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks…
Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations
Kalesha Bullard, Franziska Meier, Douwe Kiela +2
Effective communication is an important skill for enabling information exchange and cooperation in multi-agent settings. Indeed, emergent communication is now a vibrant field of re…
Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization
Dmitrii Beloborodov, A. E. Ulanov, Jakob N. Foerster +2
Quantum hardware and quantum-inspired algorithms are becoming increasingly popular for combinatorial optimization. However, these algorithms may require careful hyperparameter tuni…
Improving Policies via Search in Cooperative Partially Observable Games
Adam Lerer, Hengyuan Hu, Jakob Foerster +1
Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just…
Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning
Hengyuan Hu, Jakob N Foerster
In recent years we have seen fast progress on a number of benchmark problems in AI, with modern methods achieving near or super human performance in Go, Poker and Dota. One common…
Capacity, Bandwidth, and Compositionality in Emergent Language Learning
Cinjon Resnick, Abhinav Gupta, Jakob Foerster +2
Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compos…
Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods
Oana-Maria Camburu, Eleonora Giunchiglia, Jakob Foerster +2
For AI systems to garner widespread public acceptance, we must develop methods capable of explaining the decisions of black-box models such as neural networks. In this work, we ide…
Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning
Gregory Farquhar, Shimon Whiteson, Jakob Foerster
Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, un…
Exploratory Combinatorial Optimization with Reinforcement Learning
Thomas D. Barrett, William R. Clements, Jakob N. Foerster +1
Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With…
A Survey of Reinforcement Learning Informed by Natural Language
Jelena Luketina, Nantas Nardelli, Gregory Farquhar +5
To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it…
Differentiable Game Mechanics
Alistair Letcher, David Balduzzi, Sebastien Racaniere +4
Deep learning is built on the foundational guarantee that gradient descent on an objective function converges to local minima. Unfortunately, this guarantee fails in settings, such…
On the Pitfalls of Measuring Emergent Communication
Ryan Lowe, Jakob Foerster, Y-Lan Boureau +2
How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to…
The StarCraft Multi-Agent Challenge
Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt +7
In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partia…
The Hanabi Challenge: A New Frontier for AI Research
Nolan Bard, Jakob N. Foerster, Sarath Chandar +12
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made…
Stable Opponent Shaping in Differentiable Games
Alistair Letcher, Jakob Foerster, David Balduzzi +2
A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel -- from GANs and intrinsic curiosity t…
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
Jakob N. Foerster, Francis Song, Edward Hughes +5
When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions wi…
Multi-Agent Common Knowledge Reinforcement Learning
Christian A. Schroeder de Witt, Jakob N. Foerster, Gregory Farquhar +3
Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents' ability to coordinate their behaviour. In this paper, we show…
Pommerman: A Multi-Agent Playground
Cinjon Resnick, Wes Eldridge, David Ha +5
We present Pommerman, a multi-agent environment based on the classic console game Bomberman. Pommerman consists of a set of scenarios, each having at least four players and contain…
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt +3
In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a c…
The Mechanics of n-Player Differentiable Games
David Balduzzi, Sebastien Racaniere, James Martens +3
The cornerstone underpinning deep learning is the guarantee that gradient descent on an objective converges to local minima. Unfortunately, this guarantee fails in settings, such a…
DiCE: The Infinitely Differentiable Monte-Carlo Estimator
Jakob Foerster, Gregory Farquhar, Maruan Al-Shedivat +3
The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), eg, in reinforcement learning and meta-learnin…
Learning with Opponent-Learning Awareness
Jakob N. Foerster, Richard Y. Chen, Maruan Al-Shedivat +3
Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be exten…
Fake News in Social Networks
Christoph Aymanns, Jakob Foerster, Co-Pierre Georg +1
We propose multi-agent reinforcement learning as a new method for modeling fake news in social networks. This method allows us to model human behavior in social networks both in un…