Relational inductive biases, deep learning, and graph networks
- P. Battaglia, Jessica B. Hamrick, Razvan Pascanu
- Computer ScienceArXiv
- 4 June 2018
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.
The Hanabi Challenge: A New Frontier for AI Research
- Nolan Bard, Jakob N. Foerster, Michael H. Bowling
- Computer ScienceArtificial Intelligence
- 2 February 2019
Machine Theory of Mind
- Neil C. Rabinowitz, Frank Perbet, H. F. Song, Chiyuan Zhang, S. Eslami, M. Botvinick
- Computer ScienceInternational Conference on Machine Learning
- 21 February 2018
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.
Stabilizing Transformers for Reinforcement Learning
- Emilio Parisotto, H. F. Song, R. Hadsell
- Computer ScienceInternational Conference on Machine Learning
- 13 October 2019
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.
Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework
- H. F. Song, G. R. Yang, Xiao-Jing Wang
- Computer Science, BiologyPLoS Comput. Biol.
- 1 February 2016
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.
Task representations in neural networks trained to perform many cognitive tasks
- G. R. Yang, Madhura R. Joglekar, H. F. Song, W. Newsome, Xiao-Jing Wang
- Psychology, BiologyNature Neuroscience
- 14 January 2019
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.
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
- Jakob N. Foerster, H. F. Song, Michael H. Bowling
- Computer ScienceInternational Conference on Machine Learning
- 4 November 2018
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.
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
- H. F. Song, A. Abdolmaleki, M. Botvinick
- Computer ScienceInternational Conference on Learning…
- 26 September 2019
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.
Reward-based training of recurrent neural networks for cognitive and value-based tasks
- H. F. Song, G. R. Yang, Xiao-Jing Wang
- Computer Science, PsychologybioRxiv
- 19 August 2016
Trained neural network models, which exhibit many features observed in neural recordings from behaving animals and whose activity and connectivity can be fully analyzed, may provide insights into…
Relational Forward Models for Multi-Agent Learning
- A. Tacchetti, H. F. Song, P. Battaglia
- Computer ScienceInternational Conference on Learning…
- 27 September 2018
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.
...
...