367 citations · 444 across the 11 of their papers we have counts for
9 papers · 1 filter
How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models
Dharshan Kumaran, Stephen M Fleming, Larisa Markeeva +8
Large language models (LLMs) exhibit strikingly conflicting behaviors: they can appear steadfastly overconfident in their initial answers whilst at the same time being prone to exc…
Using Forwards-Backwards Models to Approximate MDP Homomorphisms
Augustine N. Mavor-Parker, Matthew J. Sargent, Christian Pehle +3
Reinforcement learning agents must painstakingly learn through trial and error what sets of state-action pairs are value equivalent -- requiring an often prohibitively large amount…
The CLRS Algorithmic Reasoning Benchmark
Petar Veličković, Adrià Puigdomènech Badia, David Budden +5
Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms. Several important works h…
Semantic Exploration from Language Abstractions and Pretrained Representations
Allison C. Tam, Neil C. Rabinowitz, Andrew K. Lampinen +6
Effective exploration is a challenge in reinforcement learning (RL). Novelty-based exploration methods can suffer in high-dimensional state spaces, such as continuous partially-obs…
Retrieval-Augmented Reinforcement Learning
Anirudh Goyal, Abram L. Friesen, Andrea Banino +13
Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has se…
CoBERL: Contrastive BERT for Reinforcement Learning
Andrea Banino, Adrià Puidomenech Badia, Jacob Walker +3
Many reinforcement learning (RL) agents require a large amount of experience to solve tasks. We propose Contrastive BERT for RL (CoBERL), an agent that combines a new contrastive l…
PonderNet: Learning to Ponder
Andrea Banino, Jan Balaguer, Charles Blundell
In standard neural networks the amount of computation used grows with the size of the inputs, but not with the complexity of the problem being learnt. To overcome this limitation w…
Towards mental time travel: a hierarchical memory for reinforcement learning agents
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Andrea Banino +1
Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrat…
MEMO: A Deep Network for Flexible Combination of Episodic Memories
Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster +7
Recent research developing neural network architectures with external memory have often used the benchmark bAbI question and answering dataset which provides a challenging number o…