91 citations · 332 across the 44 of their papers we have counts for
45 papers
Imagined Autocurricula
Ahmet H. Güzel, Matthew Thomas Jackson, Jarek Luca Liesen +4
Training agents to act in embodied environments typically requires vast training data or access to accurate simulation, neither of which exists for many cases in the real world. In…
Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
Davide Paglieri, Bartłomiej Cupiał, Jonathan Cook +6
Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods lik…
Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
Ahmet H. Güzel, Ilija Bogunovic, Jack Parker-Holder
Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, pol…
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
Davide Paglieri, Bartłomiej Cupiał, Samuel Coward +10
Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well i…
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…
Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs
Davide Paglieri, Saurabh Dash, Tim Rocktäschel +1
Post-Training Quantization (PTQ) enhances the efficiency of Large Language Models (LLMs) by enabling faster operation and compatibility with more accessible hardware through reduce…
Video as the New Language for Real-World Decision Making
Sherry Yang, Jacob Walker, Jack Parker-Holder +5
Both text and video data are abundant on the internet and support large-scale self-supervised learning through next token or frame prediction. However, they have not been equally l…
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…
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Mikayel Samvelyan, Sharath Chandra Raparthy, Andrei Lupu +9
As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to adversarial attacks is of paramou…
Multi-Agent Diagnostics for Robustness via Illuminated Diversity
Mikayel Samvelyan, Davide Paglieri, Minqi Jiang +2
In the rapidly advancing field of multi-agent systems, ensuring robustness in unfamiliar and adversarial settings is crucial. Notwithstanding their outstanding performance in famil…
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…
Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design
Matthew Thomas Jackson, Minqi Jiang, Jack Parker-Holder +5
The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is…
Stabilizing Unsupervised Environment Design with a Learned Adversary
Ishita Mediratta, Minqi Jiang, Jack Parker-Holder +3
A key challenge in training generally-capable agents is the design of training tasks that facilitate broad generalization and robustness to environment variations. This challenge m…
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Mikayel Samvelyan, Akbir Khan, Michael Dennis +5
Open-ended learning methods that automatically generate a curriculum of increasingly challenging tasks serve as a promising avenue toward generally capable reinforcement learning a…
Synthetic Experience Replay
Cong Lu, Philip J. Ball, Yee Whye Teh +1
A key theme in the past decade has been that when large neural networks and large datasets combine they can produce remarkable results. In deep reinforcement learning (RL), this pa…
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…
The Effectiveness of World Models for Continual Reinforcement Learning
Samuel Kessler, Mateusz Ostaszewski, Michał Bortkiewicz +5
World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the…
Learning General World Models in a Handful of Reward-Free Deployments
Yingchen Xu, Jack Parker-Holder, Aldo Pacchiano +5
Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate…
Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Michael Matthews, Mikayel Samvelyan, Jack Parker-Holder +2
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually tra…
Bayesian Generational Population-Based Training
Xingchen Wan, Cong Lu, Jack Parker-Holder +4
Reinforcement learning (RL) offers the potential for training generally capable agents that can interact autonomously in the real world. However, one key limitation is the brittlen…
Grounding Aleatoric Uncertainty for Unsupervised Environment Design
Minqi Jiang, Michael Dennis, Jack Parker-Holder +5
Adaptive curricula in reinforcement learning (RL) have proven effective for producing policies robust to discrepancies between the train and test environment. Recently, the Unsuper…
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
Cong Lu, Philip J. Ball, Tim G. J. Rudner +3
Offline reinforcement learning has shown great promise in leveraging large pre-collected datasets for policy learning, allowing agents to forgo often-expensive online data collecti…
Insights From the NeurIPS 2021 NetHack Challenge
Eric Hambro, Sharada Mohanty, Dmitrii Babaev +26
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' i…
On-the-fly Strategy Adaptation for ad-hoc Agent Coordination
Jaleh Zand, Jack Parker-Holder, Stephen J. Roberts
Training agents in cooperative settings offers the promise of AI agents able to interact effectively with humans (and other agents) in the real world. Multi-agent reinforcement lea…