150 citations · 189 across the 3 of their papers we have counts for
5 papers · 1 filter
Can foundation models actively gather information in interactive environments to test hypotheses?
Danny P. Sawyer, Nan Rosemary Ke, Hubert Soyer +9
Foundation models excel at single-turn reasoning but struggle with multi-turn exploration in dynamic environments, a requirement for many real-world challenges. We evaluated these…
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Tom Le Paine, Caglar Gulcehre, Bobak Shahriari +11
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial…
Multi-task Deep Reinforcement Learning with PopArt
Matteo Hessel, Hubert Soyer, Lasse Espeholt +3
The reinforcement learning community has made great strides in designing algorithms capable of exceeding human performance on specific tasks. These algorithms are mostly trained on…
Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
Thomas Stepleton, Razvan Pascanu, Will Dabney +3
Reinforcement learning (RL) agents performing complex tasks must be able to remember observations and actions across sizable time intervals. This is especially true during the init…
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Lasse Espeholt, Hubert Soyer, Remi Munos +9
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amo…