Jean-Baptiste Gaya

3 papers · 2022–2023 · 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 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICLR (2) NeurIPS (1)

Top co-authors

Laure Soulier (3) Ludovic DENOYER (2) Matthieu Cord (1) Thang Doan (1) Alexandre Rame (1) Lucas Caccia (1) Corentin Dancette (1) Mustafa Shukor (1) Roberta Raileanu (1) Guillaume Couairon (1)

Research topics

Reinforcement Learning (3) Methods (3) Machine Learning (2) Application Areas (2) Artificial Intelligence (1) Applications (1) Core AI (1) Learning Paradigms (1) Optimization & Theory (1)

Keywords

reinforcement learning (2) policy subspace (2) catastrophic forgetting (1) domain generalization (1) reinforcement learning from human feedback (1) model alignment (1) multi-objective learning (1) weight interpolation (1) parameter space (1) online adaptation (1) pareto optimization (1) positive transfer (1) continual learning (1)

Papers

Building a Subspace of Policies for Scalable Continual Learning ICLR 2023 Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards NeurIPS 2023 Learning a subspace of policies for online adaptation in Reinforcement Learning ICLR 2022