Michel Ma

3 papers · 2023–2024 · 3 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 ❓ The Questioner (2)

Venues

ICLR (1) ICML (1) NeurIPS (1)

Top co-authors

Tianwei Ni (3) Pierre-Luc Bacon (3) Benjamin Eysenbach (2) Clement Gehring (2) Erfan SeyedSalehi (1) Aditya Mahajan (1) Pierluca D’Oro (1)

Research topics

Deep Learning (2) Machine Learning (2) Reinforcement Learning (2) Architectures (2) Core Methods (2) Methods (2) Artificial Intelligence (1) Core AI (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1)

Keywords

reinforcement learning (2) representation learning (1) policy gradient (1) self-supervised learning (1) transformer (1) partially observable markov decision process (1) world model (1) credit assignment (1) long-term dependency (1) gradient propagation (1) long-horizon task (1) long-term dependencies (1) transformer architecture (1) action-conditioned (1)

Papers

Bridging State and History Representations: Understanding Self-Predictive RL ICLR 2024 Do Transformer World Models Give Better Policy Gradients? ICML 2024 When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment NeurIPS 2023