Yannis Flet-Berliac

9 papers · 2020–2024 · 6 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 · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze

Venues

NeurIPS (3) ICLR (2) AAAI (1) EMNLP (1) IJCAI (1) UAI (1)

Top co-authors

Emma Brunskill (5) Allen Nie (4) Philippe Preux (3) Yash Chandak (2) Olivier Pietquin (2) Anirudhan Badrinath (2) Matthieu Geist (2) Yao Liu (1) Florian Strub (1) Nathan Grinsztajn (1)

Research topics

Reinforcement Learning (9) Methods (9) Machine Learning (6) Learning Types · Machine Learning (5) Artificial Intelligence (3) Deep Learning (3) Core AI (3) Learning Types · Deep Learning (3) Optimization & Theory (3) Application Areas (2) Applications (2) Models (1)

Keywords

offline reinforcement learning (3) policy gradient (3) continuous control (2) reinforcement learning (2) sample efficiency (2) policy learning (1) preference optimization (1) risk management (1) kl divergence (1) sequential decision making (1) adversarial learning (1) supervised learning (1) model-based reinforcement learning (1) model alignment (1) value function (1) importance sampling (1) model misspecification (1) contrastive learning (1) value function approximation (1) deep reinforcement learning (1)

Papers

Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion EMNLP 2024 OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators NeurIPS 2024 Model-Based Offline Reinforcement Learning with Local Misspecification AAAI 2023 Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets NeurIPS 2023 Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data NeurIPS 2022 Offline policy optimization with eligible actions UAI 2022 Adversarially Guided Actor-Critic ICLR 2021 Learning Value Functions in Deep Policy Gradients using Residual Variance ICLR 2021 Only Relevant Information Matters: Filtering Out Noisy Samples To Boost RL IJCAI 2020