91 citations · 332 across the 44 of their papers we have counts for
37 papers · 1 filter
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…
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…
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…
Evolving Curricula with Regret-Based Environment Design
Jack Parker-Holder, Minqi Jiang, Michael Dennis +4
It remains a significant challenge to train generally capable agents with reinforcement learning (RL). A promising avenue for improving the robustness of RL agents is through the u…
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
Jack Parker-Holder, Raghu Rajan, Xingyou Song +9
The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally capable a…
Revisiting Design Choices in Offline Model-Based Reinforcement Learning
Cong Lu, Philip J. Ball, Jack Parker-Holder +2
Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially…
Replay-Guided Adversarial Environment Design
Minqi Jiang, Michael Dennis, Jack Parker-Holder +3
Deep reinforcement learning (RL) agents may successfully generalize to new settings if trained on an appropriately diverse set of environment and task configurations. Unsupervised…
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
Mikayel Samvelyan, Robert Kirk, Vitaly Kurin +7
Progress in deep reinforcement learning (RL) is heavily driven by the availability of challenging benchmarks used for training agents. However, benchmarks that are widely adopted b…
From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers
Krzysztof Choromanski, Han Lin, Haoxian Chen +7
In this paper we provide, to the best of our knowledge, the first comprehensive approach for incorporating various masking mechanisms into Transformers architectures in a scalable…