188 citations · 221 across the 12 of their papers we have counts for
12 papers
Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions
J Rosser, Robert Kirk, Edward Grefenstette +2
Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework,…
Investigating Non-Transitivity in LLM-as-a-Judge
Yi Xu, Laura Ruis, Tim Rocktäschel +1
Automatic evaluation methods based on large language models (LLMs) are emerging as the standard tool for assessing the instruction-following abilities of LLM-based agents. The most…
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
Laura Ruis, Maximilian Mozes, Juhan Bae +7
The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand,…
Leading the Pack: N-player Opponent Shaping
Alexandra Souly, Timon Willi, Akbir Khan +4
Reinforcement learning solutions have great success in the 2-player general sum setting. In this setting, the paradigm of Opponent Shaping (OS), in which agents account for the lea…
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
Samyak Jain, Robert Kirk, Ekdeep Singh Lubana +5
Fine-tuning large pre-trained models has become the de facto strategy for developing both task-specific and general-purpose machine learning systems, including developing models th…
Understanding the Effects of RLHF on LLM Generalisation and Diversity
Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis +4
Large language models (LLMs) fine-tuned with reinforcement learning from human feedback (RLHF) have been used in some of the most widely deployed AI models to date, such as OpenAI'…
Reward Model Ensembles Help Mitigate Overoptimization
Thomas Coste, Usman Anwar, Robert Kirk +1
Reinforcement learning from human feedback (RLHF) is a standard approach for fine-tuning large language models to follow instructions. As part of this process, learned reward model…
Domain Generalization for Robust Model-Based Offline Reinforcement Learning
Alan Clark, Shoaib Ahmed Siddiqui, Robert Kirk +3
Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider…
Graph Backup: Data Efficient Backup Exploiting Markovian Transitions
Zhengyao Jiang, Tianjun Zhang, Robert Kirk +2
The successes of deep Reinforcement Learning (RL) are limited to settings where we have a large stream of online experiences, but applying RL in the data-efficient setting with lim…
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…
A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
Robert Kirk, Amy Zhang, Edward Grefenstette +1
The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deploymen…
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…