1.3k citations · 6.3k across the 48 of their papers we have counts for
7 papers · 1 filter
Representation Learning via Invariant Causal Mechanisms
Jovana Mitrovic, Brian McWilliams, Jacob Walker +2
Self-supervised learning has emerged as a strategy to reduce the reliance on costly supervised signal by pretraining representations only using unlabeled data. These methods combin…
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Anirudh Goyal, Alex Lamb, Phanideep Gampa +5
Modeling a structured, dynamic environment like a video game requires keeping track of the objects and their states declarative knowledge) as well as predicting how objects behave…
Pointer Graph Networks
Petar Veličković, Lars Buesing, Matthew C. Overlan +3
Graph neural networks (GNNs) are typically applied to static graphs that are assumed to be known upfront. This static input structure is often informed purely by insight of the mac…
Agent57: Outperforming the Atari Human Benchmark
Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski +4
Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algor…
Never Give Up: Learning Directed Exploration Strategies
Adrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi +8
We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic rewa…
Targeted free energy estimation via learned mappings
Peter Wirnsberger, Andrew J. Ballard, George Papamakarios +5
Free energy perturbation (FEP) was proposed by Zwanzig more than six decades ago as a method to estimate free energy differences, and has since inspired a huge body of related meth…