67 citations · 191 across the 16 of their papers we have counts for
17 papers
Training Language Models to Self-Correct via Reinforcement Learning
Aviral Kumar, Vincent Zhuang, Rishabh Agarwal +15
Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for t…
Open-Endedness is Essential for Artificial Superhuman Intelligence
Edward Hughes, Michael Dennis, Jack Parker-Holder +5
In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internetscale data. Nevertheless, the c…
Many-Shot In-Context Learning
Rishabh Agarwal, Avi Singh, Lei M. Zhang +12
Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, without any weight updates. Newly expande…
Genie: Generative Interactive Environments
Jake Bruce, Michael Dennis, Ashley Edwards +22
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless…
Vision-Language Models as a Source of Rewards
Kate Baumli, Satinder Baveja, Feryal Behbahani +24
Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning. A key limiting factor for bui…
Structured State Space Models for In-Context Reinforcement Learning
Chris Lu, Yannick Schroecker, Albert Gu +4
Structured state space sequence (S4) models have recently achieved state-of-the-art performance on long-range sequence modeling tasks. These models also have fast inference speeds…
Hierarchical Reinforcement Learning in Complex 3D Environments
Bernardo Avila Pires, Feryal Behbahani, Hubert Soyer +3
Hierarchical Reinforcement Learning (HRL) agents have the potential to demonstrate appealing capabilities such as planning and exploration with abstraction, transfer, and skill reu…
Human-Timescale Adaptation in an Open-Ended Task Space
Adaptive Agent Team, Jakob Bauer, Kate Baumli +25
Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to rein…
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
Tom Zahavy, Yannick Schroecker, Feryal Behbahani +4
Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of d…
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Angelos Filos, Eszter Vértes, Zita Marinho +7
Using a model of the environment and a value function, an agent can construct many estimates of a state's value, by unrolling the model for different lengths and bootstrapping with…
On the role of planning in model-based deep reinforcement learning
Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani +7
Model-based planning is often thought to be necessary for deep, careful reasoning and generalization in artificial agents. While recent successes of model-based reinforcement learn…
Learning Compositional Neural Programs for Continuous Control
Thomas Pierrot, Nicolas Perrin, Feryal Behbahani +4
We propose a novel solution to challenging sparse-reward, continuous control problems that require hierarchical planning at multiple levels of abstraction. Our solution, dubbed Alp…
Acme: A Research Framework for Distributed Reinforcement Learning
Matthew W. Hoffman, Bobak Shahriari, John Aslanides +36
Deep reinforcement learning (RL) has led to many recent and groundbreaking advances. However, these advances have often come at the cost of both increased scale in the underlying a…
Privileged Information Dropout in Reinforcement Learning
Pierre-Alexandre Kamienny, Kai Arulkumaran, Feryal Behbahani +2
Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning…
Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
Tianhong Dai, Kai Arulkumaran, Tamara Gerbert +3
Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practi…
Modular Meta-Learning with Shrinkage
Yutian Chen, Abram L. Friesen, Feryal Behbahani +4
Many real-world problems, including multi-speaker text-to-speech synthesis, can greatly benefit from the ability to meta-learn large models with only a few task-specific components…
Learning from Demonstration in the Wild
Feryal Behbahani, Kyriacos Shiarlis, Xi Chen +8
Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically…