• Publications
  • Influence
Relational inductive biases, deep learning, and graph networks
TLDR
It is argued that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Expand
Machine Theory of Mind
TLDR
It is argued that this system -- which autonomously learns how to model other agents in its world -- is an important step forward for developing multi-agent AI systems, for building intermediating technology for machine-human interaction, and for advancing the progress on interpretable AI. Expand
Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework
TLDR
A framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge is described and an implementation based on the machine learning library Theano is provided, whose automatic differentiation capabilities facilitate modifications and extensions. Expand
The Hanabi Challenge: A New Frontier for AI Research
TLDR
It is argued that Hanabi elevates reasoning about the beliefs and intentions of other agents to the foreground and developing novel techniques for such theory of mind reasoning will not only be crucial for success in Hanabi, but also in broader collaborative efforts, especially those with human partners. Expand
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
TLDR
The Bayesian action decoder (BAD), a new multi-agent learning method that uses an approximate Bayesian update to obtain a public belief that conditions on the actions taken by all agents in the environment are met, is presented. Expand
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
TLDR
V-MPO is introduced, an on-policy adaptation of Maximum a Posteriori Policy Optimization that performs policy iteration based on a learned state-value function and does so reliably without importance weighting, entropy regularization, or population-based tuning of hyperparameters. Expand
Stabilizing Transformers for Reinforcement Learning
TLDR
The proposed architecture, the Gated Transformer-XL (GTrXL), surpasses LSTMs on challenging memory environments and achieves state-of-the-art results on the multi-task DMLab-30 benchmark suite, exceeding the performance of an external memory architecture. Expand
Task representations in neural networks trained to perform many cognitive tasks
TLDR
It is found that after training, recurrent units can develop into clusters that are functionally specialized for different cognitive processes, and a simple yet effective measure is introduced to quantify relationships between single-unit neural representations of tasks. Expand
Reward-based training of recurrent neural networks for cognitive and value-based tasks
TLDR
This work implements reward-based training of recurrent neural networks in which a value network guides learning by using the activity of the decision network to predict future reward, and predicts a role for value representation that is essential for learning, but not executing, a task. Expand
Relational Forward Models for Multi-Agent Learning
TLDR
Relational Forward Models (RFM) for multi-agent learning are introduced, networks that can learn to make accurate predictions of agents' future behavior in multi- agent environments. Expand
...
1
2
3
...