Tom Schaul

22 papers · 2010–2025 · 6 conferences · across top CS/AI conferences

Achievements

+12 more ↓

🏃 Academic Marathon (15) 🌍 Conference Polyglot (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (5)

🧭 Keyword Pioneer 🐝 Cross-Pollinator (5) 🌍 Conference Polyglot (6) 🌟 Keyword Trendsetter Combo (3) 👑 Triple Crown 🧬 Topic Evolution 📈 Trend Setter 🚀 Conference Pioneer 🗃️ Keyword Collector (66) 🔥 Unstoppable (8) ❓ The Questioner 💎 Century Club (22)

Conferences

ICML (9) NIPS (5) ICLR (3) IJCAI (2) JMLR (2) AISTATS (1)

Top co-authors

Andre Barreto (7) David Silver (7) Rémi Munos (5) Diana Borsa (4) Hado Hasselt (3) Georg Ostrovski (3) Matteo Hessel (3) John Quan (3) Hado P van Hasselt (2) Feryal Behbahani (2)

Keywords

reinforcement learning (5) value function (3) deep reinforcement learning (2) policy gradient (2) sparse reward (2) transfer learning (2) policy improvement (2) successor feature (2) neural network architecture (2) black-box optimization (1) deep learning (1) supervised learning (1) neural network optimization (1) hierarchical reinforcement learning (1) policy optimization (1) epistemic uncertainty (1) gradient descent (1) function approximation (1) bellman equation (1) importance sampling (1)

Papers

AuPair: Golden Example Pairs for Code Repair ICML 2025 Position: Open-Endedness is Essential for Artificial Superhuman Intelligence ICML 2024 Scaling Goal-based Exploration via Pruning Proto-goals IJCAI 2023 Discovering Evolution Strategies via Meta-Black-Box Optimization ICLR 2023 The Phenomenon of Policy Churn NIPS 2022 When should agents explore? ICLR 2022 Model-Value Inconsistency as a Signal for Epistemic Uncertainty ICML 2022 Conditional Importance Sampling for Off-Policy Learning AISTATS 2020 Universal Successor Features Approximators ICLR 2019 Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement ICML 2018 Natural Value Approximators: Learning when to Trust Past Estimates NIPS 2017 Successor Features for Transfer in Reinforcement Learning NIPS 2017 The Predictron: End-To-End Learning and Planning ICML 2017 FeUdal Networks for Hierarchical Reinforcement Learning ICML 2017 Unifying Count-Based Exploration and Intrinsic Motivation NIPS 2016 Learning to learn by gradient descent by gradient descent NIPS 2016 Dueling Network Architectures for Deep Reinforcement Learning ICML 2016 Universal Value Function Approximators ICML 2015 Natural Evolution Strategies JMLR 2014 Better Generalization with Forecasts IJCAI 2013 No more pesky learning rates ICML 2013 PyBrain JMLR 2010