Thomas Furmston

3 papers · 2010–2016 · 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 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

AISTATS (1) JMLR (1) NeurIPS (1)

Top co-authors

David Barber (3) Guy Lever (1)

Research topics

Machine Learning (3) Reinforcement Learning (3) Methods (3) Optimization & Theory (3) Mathematics & Optimization (1) Bayesian & Probabilistic (1) Learning Types (1) Optimization (1)

Keywords

markov decision process (3) natural gradient (2) policy search (2) approximate newton method (2) convergence analysis (1) expectation maximization (1) expectation propagation (1) parametric optimization (1) gauss-newton method (1) variational baye (1) newton method (1) natural gradient ascent (1) reinforcement learning (1) parametric policy search (1) variational inference (1) bayesian learning (1) markov decision processes (1)

Papers

Approximate Newton Methods for Policy Search in Markov Decision Processes JMLR 2016 A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes NeurIPS 2012 Variational methods for Reinforcement Learning AISTATS 2010