Stefano V Albrecht

8 papers · 2021–2025 · 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 🗺️ Taxonomy Completionist (18) 🔥 Unstoppable · Bronze

Venues

ICLR (5) ICML (3)

Top co-authors

Shangmin Guo (3) Kenny Smith (2) Christopher G. Lucas (2) Filippos Christianos (2) Trevor McInroe (2) Yi Ren (2) Muhammad A Rahman (2) Samuel Garcin (2) Haobo Fu (1) Kevin Sebastian Luck (1)

Research topics

Machine Learning (5) Reinforcement Learning (4) Methods (4) Artificial Intelligence (3) Core AI (3) Learning Types (3) Deep Learning (2) Core Methods (2) Optimization & Theory (2) Application Areas (1) Applications (1) Architectures (1) Models (1)

Keywords

reinforcement learning (3) representation learning (2) sample efficiency (2) policy optimization (1) self-supervised learning (1) supervised learning (1) policy learning (1) mutual information (1) parameter sharing (1) weight update (1) generative model (1) generalization bound (1) disentangled representation (1) reward model (1) poisoning attack (1) zero-shot transfer (1) human preference (1) contrastive loss (1) ad hoc teamwork (1) emergent language (1)

Papers

Online-to-Offline RL for Agent Alignment ICLR 2025 Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning ICLR 2025 DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design ICML 2024 lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning ICLR 2024 Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning ICLR 2023 Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability ICLR 2022 Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing ICML 2021 Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning ICML 2021