498 citations · 1.8k across the 31 of their papers we have counts for
5 papers · 1 filter
Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning
Wilka Carvalho, Andrew Lampinen, Kyriacos Nikiforou +2
Many important tasks are defined in terms of object. To generalize across these tasks, a reinforcement learning (RL) agent needs to exploit the structure that the objects induce. P…
In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications
Borja G. León, Murray Shanahan, Francesco Belardinelli
We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinfor…
Integrated information as a common signature of dynamical and information-processing complexity
Pedro A. M. Mediano, Fernando E. Rosas, Juan Carlos Farah +3
The apparent dichotomy between information-processing and dynamical approaches to complexity science forces researchers to choose between two diverging sets of tools and explanatio…
Encoders and Ensembles for Task-Free Continual Learning
Murray Shanahan, Christos Kaplanis, Jovana Mitrović
We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to…
Unsupervised Object-Based Transition Models for 3D Partially Observable Environments
Antonia Creswell, Rishabh Kabra, Chris Burgess +1
We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order a…