Profiles2021-2025
Nicolas Le Roux
Microsoft Research
3Papers
2Last author
5Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers3
- Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language modelsAuthor 1 of 11NeurIPS 2025 · 5 citations
- Decision-Aware Actor-Critic with Function Approximation and Theoretical GuaranteesAuthor 4 of 4NeurIPS 2023 · 6 citations
- Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy OptimizationAuthor 4 of 4ICML 2021 · 35 citations
