Thomas Mesnard

6 papers · 2019–2024 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

ICML (5) NeurIPS (1)

Top co-authors

Rémi Munos (5) Will Dabney (3) Michal Valko (3) Eric Moulines (2) Yunhao Tang (2) Nicolas Heess (2) Doina Precup (2) Alaa Saade (2) Anna Harutyunyan (2) Mark Rowland (2)

Research topics

Reinforcement Learning (6) Methods (6) Artificial Intelligence (4) Machine Learning (4) Core AI (4) Learning Types (3) Optimization & Theory (2) Natural Language Processing (1) Generation (1)

Keywords

credit assignment (3) variance reduction (2) policy gradient (2) value function (2) large language model (2) distributional reinforcement learning (1) nash equilibrium (1) mirror descent (1) value estimation (1) curiosity-driven learning (1) intrinsic motivation (1) human feedback (1) reward model (1) counterfactual reasoning (1) model-free reinforcement learning (1) stochastic environment (1) intrinsic exploration (1) curiosity-driven exploration (1) distributional value estimation (1) rlhf (1)

Papers

Nash Learning from Human Feedback ICML 2024 RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback ICML 2024 Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments ICML 2023 Quantile Credit Assignment ICML 2023 Counterfactual Credit Assignment in Model-Free Reinforcement Learning ICML 2021 Hindsight Credit Assignment NeurIPS 2019