Ryan Lowe
Founder of Meaning Alignment Institute; previously OpenAI alignment lead; co-author of InstructGPT.
- Role
- founder
- Currently at
- Independent
- twitter.com/ryan_t_lowe
- GitHub
- github.com/rlowe
- Scholar
- scholar.google.com/citations
- Papers
- 6
Cite
Notes
Only stored in your browser.
Authored papers
6GPT-4 Technical Report
gpt-4-technical-report
Training language models to follow instructions with human feedback
NeurIPS
Learning an Unreferenced Metric for Online Dialogue Evaluation
learning-an-unreferenced-metric-for-online-1
On the interaction between supervision and self-play in emergent communication
ICLR 2020 1
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
multi-agent-actor-critic-for-mixed-1
The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems
the-ubuntu-dialogue-corpus-a-large-dataset
Affiliations
Frequent co-authors
10from 6 papers
Joelle Pineau
Chief AI Officer
Carroll Wainwright
researcher
Chong Zhang
researcher
Diogo Almeida
researcher
Jan Leike
researcher
Jeff Wu
researcher
John Schulman
co-founder
Katarina Slama
researcher
Long Ouyang
researcher
Maddie Simens
researcher