Follow
Robert Kirk
Robert Kirk
Research Scientist, UK AI Safety Institute
Verified email at dsit.gov.uk - Homepage
Title
Cited by
Cited by
Year
A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
R Kirk, A Zhang, E Grefenstette, T Rocktäschel
Journal of Artificial Intelligence Research 76, 201-264, 2023
3902023
MiniHack the Planet: A Sandbox for Open-ended Reinforcement Learning Research
M Samvelyan, R Kirk, V Kurin, J Parker-Holder, M Jiang, E Hambro, ...
NeurIPS 2021 Datasets and Benchmarks Track, 2021
952021
Reward Model Ensembles Help Mitigate Overoptimization
T Coste, U Anwar, R Kirk, D Krueger
ICLR 2024, 2023
702023
Understanding the Effects of RLHF on LLM Generalisation and Diversity
R Kirk, I Mediratta, C Nalmpantis, J Luketina, E Hambro, E Grefenstette, ...
ICLR 2024, 2023
692023
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
S Jain, R Kirk, ES Lubana, RP Dick, H Tanaka, E Grefenstette, ...
ICLR 2024, 2023
412023
Insights from the neurips 2021 nethack challenge
E Hambro, S Mohanty, D Babaev, M Byeon, D Chakraborty, ...
NeurIPS 2021 Competitions and Demonstrations Track, 41-52, 2022
222022
Generalization to new sequential decision making tasks with in-context learning
SC Raparthy, E Hambro, R Kirk, M Henaff, R Raileanu
ICML 2024, 2023
122023
A study of off-policy learning in environments with procedural content generation
A Ehrenberg, R Kirk, M Jiang, E Grefenstette, T Rocktäschel
ICLR Workshop on Agent Learning in Open-Endedness, 2022
62022
Analyzing the Generalization and Reliability of Steering Vectors
D Tan, D Chanin, A Lynch, D Kanoulas, B Paige, A Garriga-Alonso, R Kirk
arXiv preprint arXiv:2407.12404, 2024
52024
Graph backup: Data efficient backup exploiting markovian transitions
Z Jiang, T Zhang, R Kirk, T Rocktäschel, E Grefenstette
arXiv preprint arXiv:2205.15824, 2022
4*2022
Leading the Pack: N-player Opponent Shaping
A Souly, T Willi, A Khan, R Kirk, C Lu, E Grefenstette, T Rocktäschel
arXiv preprint arXiv:2312.12564, 2023
32023
Domain Generalization for Robust Model-Based Offline Reinforcement Learning
A Clark, SA Siddiqui, R Kirk, U Anwar, S Chung, D Krueger
arXiv preprint arXiv:2211.14827, 2022
12022
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
L Ruis, M Mozes, J Bae, SR Kamalakara, D Talupuru, A Locatelli, R Kirk, ...
arXiv preprint arXiv:2411.12580, 2024
2024
What Mechanisms Does Knowledge Distillation Distill?
C Wu, ES Lubana, BK Mlodozeniec, R Kirk, D Krueger
Proceedings of UniReps: the First Workshop on Unifying Representations in …, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–14