1 code implementation • 7 Nov 2023 • Diogo Cruz, Edoardo Pona, Alex Holness-Tofts, Elias Schmied, Víctor Abia Alonso, Charlie Griffin, Bogdan-Ionut Cirstea
Many capable large language models (LLMs) are developed via self-supervised pre-training followed by a reinforcement-learning fine-tuning phase, often based on human or AI feedback.
no code implementations • 18 Oct 2023 • Rohan Subramani, Marcus Williams, Max Heitmann, Halfdan Holm, Charlie Griffin, Joar Skalse
However, it is well-known that certain tasks cannot be expressed by means of an objective in the Markov rewards formalism, motivating the study of alternative objective-specification formalisms in RL such as Linear Temporal Logic and Multi-Objective Reinforcement Learning.
Multi-Objective Reinforcement Learning reinforcement-learning
no code implementations • 13 Oct 2023 • Jacek Karwowski, Oliver Hayman, Xingjian Bai, Klaus Kiendlhofer, Charlie Griffin, Joar Skalse
First, we propose a way to quantify the magnitude of this effect and show empirically that optimising an imperfect proxy reward often leads to the behaviour predicted by Goodhart's law for a wide range of environments and reward functions.
1 code implementation • 28 Dec 2022 • Joar Skalse, Lewis Hammond, Charlie Griffin, Alessandro Abate
In this work we introduce reinforcement learning techniques for solving lexicographic multi-objective problems.
Multi-Objective Reinforcement Learning reinforcement-learning
no code implementations • 11 Mar 2021 • Peiyang He, Charlie Griffin, Krzysztof Kacprzyk, Artjom Joosen, Michael Collyer, Aleksandar Shtedritski, Yuki M. Asano
Privacy considerations and bias in datasets are quickly becoming high-priority issues that the computer vision community needs to face.