Folgen
Timon Willi
Timon Willi
University of Oxford
Bestätigte E-Mail-Adresse bei eng.ox.ac.uk - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Model-Free Opponent Shaping
C Lu, T Willi, CAS De Witt, J Foerster
International Conference on Machine Learning, 2022
492022
Consistent Learning with Opponent-Learning Awareness
T Willi*, AH Letcher*, J Treutlein*, J Foerster
International Conference on Machine Learning, 2022
472022
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
A Rutherford*, B Ellis*, M Gallici*, J Cook*, A Lupu*, G Ingvarsson*, ...
Proceedings of the 23rd International Conference on Autonomous Agents and …, 2024
27*2024
Adversarial Cheap Talk
C Lu, T Willi, A Letcher, JN Foerster
Decision Awareness in Reinforcement Learning Workshop at ICML 2022, 2022
212022
Recurrent Neural Processes
T Willi, J Masci, J Schmidhuber, C Osendorfer
arXiv preprint arXiv:1906.05915, 2019
202019
Mixtures of Experts Unlock Parameter Scaling for Deep RL
JSO Ceron*, G Sokar*, T Willi*, C Lyle, J Farebrother, JN Foerster, ...
Forty-first International Conference on Machine Learning (spotlight, 3.5%), 2024
8*2024
Scaling Opponent Shaping to High Dimensional Games
A Khan*, T Willi*, N Kwan*, A Tacchetti, C Lu, E Grefenstette, ...
arXiv preprint arXiv:2312.12568, 2023
6*2023
Analysing the Sample Complexity of Opponent Shaping
K Fung, Q Zhang, C Lu, J Wan, T Willi, J Foerster
arXiv preprint arXiv:2402.05782, 2024
3*2024
Pax: Scalable Opponent Shaping in Jax
T Willi, A Khan, N Kwan, M Samvelyan, C Lu, J Foerster
2*2023
Mixture of Experts in a Mixture of RL settings
T Willi, J Obando-Ceron, J Foerster, K Dziugaite, PS Castro
arXiv preprint arXiv:2406.18420, 2024
12024
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
12023
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
A Rutherford, M Beukman, T Willi, B Lacerda, N Hawes, J Foerster
arXiv preprint arXiv:2408.15099, 2024
2024
The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games
J Levi, C Lu, T Willi, CS de Witt, J Foerster
arXiv preprint arXiv:2402.01088, 2024
2024
Jafar: An Open-Source Genie Reimplemention in Jax
T Willi, MT Jackson, JN Foerster
First Workshop on Controllable Video Generation@ ICML24, 2024
2024
Evaluation of Word Embeddings for Stance Detection in Tweets
T Willi
Bachelor's Thesis, University of Zurich, 2017
2017
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–15