Adrien Ecoffet
Adrien Ecoffet
Research Scientist, OpenAI
Verifisert e-postadresse på openai.com - Startside
Tittel
Sitert av
Sitert av
År
Go-explore: a new approach for hard-exploration problems
A Ecoffet, J Huizinga, J Lehman, KO Stanley, J Clune
arXiv preprint arXiv:1901.10995, 2019
2142019
First return, then explore
A Ecoffet, J Huizinga, J Lehman, KO Stanley, J Clune
Nature 590 (7847), 580-586, 2021
572021
Exploration based language learning for text-based games
A Madotto, M Namazifar, J Huizinga, P Molino, A Ecoffet, H Zheng, ...
International Joint Conferences on Artificial Intelligence, 1488-1494, 2020
132020
Montezuma’s revenge solved by go-explore, a new algorithm for hard-exploration problems (sets records on pitfall, too)
A Ecoffet, J Huizinga, J Lehman, KO Stanley, J Clune
Uber Engineering Blog, Nov, 2018
122018
Reinforcement learning under moral uncertainty
A Ecoffet, J Lehman
International Conference on Machine Learning, 2926-2936, 2021
62021
Estimating Q(s, s’) with deep deterministic dynamics gradients
A Edwards, H Sahni, R Liu, J Hung, A Jain, R Wang, A Ecoffet, T Miconi, ...
International Conference on Machine Learning, 2825-2835, 2020
62020
Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity
A Ecoffet, J Clune, J Lehman
Artificial Life Conference Proceedings, 27-35, 2020
12020
Commonsense and semantic-guided navigation through language in embodied environment
D Yu, C Khatri, A Papangelis, A Madotto, M Namazifar, J Huizinga, ...
ViGIL@ NeurIPS, 2019
12019
Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft
I Kanitscheider, J Huizinga, D Farhi, WH Guss, B Houghton, R Sampedro, ...
arXiv preprint arXiv:2106.14876, 2021
2021
Deep reinforcement learning based models for hard-exploration problems
JM Clune, AL Ecoffet, KO Stanley, J Huizinga, JA Lehman
US Patent App. 16/696,893, 2020
2020
Systemet kan ikke utføre handlingen. Prøv igjen senere.
Artikler 1–10