Matteo Hessel

21 papers · 2016–2022 · 4 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (4) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (6)

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🤝 Dynamic Duo (15) 👑 Triple Crown 🏆 Grand Slam 🔬 Deep Specialist (13) 🏆 Keyword Champion (2) 🔥 Unstoppable (7) ⚡ Prolific Year (6) 🗃️ Keyword Collector (75) ❓ The Questioner (2) 💎 Century Club (21) 🚀 Conference Pioneer

Conferences

NIPS (8) ICML (7) ICLR (4) AAAI (2)

Top co-authors

David Silver (15) Hado van Hasselt (8) Hado P van Hasselt (8) Zhongwen Xu (7) Junhyuk Oh (6) Satinder P. Singh (4) Andre Barreto (3) Satinder Singh (3) Vivek Veeriah (3) Tom Schaul (3)

Research topics

Reinforcement Learning (1)

Keywords

reinforcement learning (8) deep reinforcement learning (4) policy gradient (3) atari game (3) value function (3) off-policy learning (3) model-based reinforcement learning (3) experience replay (2) credit assignment (2) value function estimation (2) function approximation (2) temporal difference learning (2) reward function (2) auxiliary task (2) temporal-difference learning (2) successor feature (2) value iteration (2) hierarchical reinforcement learning (1) deep learning (1) multi-task learning (1)

Papers

Learning by Directional Gradient Descent ICLR 2022 Muesli: Combining Improvements in Policy Optimization ICML 2021 Self-Consistent Models and Values NIPS 2021 Discovery of Options via Meta-Learned Subgoals NIPS 2021 Expected Eligibility Traces AAAI 2021 Emphatic Algorithms for Deep Reinforcement Learning ICML 2021 A Self-Tuning Actor-Critic Algorithm NIPS 2020 Behaviour Suite for Reinforcement Learning ICLR 2020 Off-Policy Actor-Critic with Shared Experience Replay ICML 2020 Discovering Reinforcement Learning Algorithms NIPS 2020 Meta-Gradient Reinforcement Learning with an Objective Discovered Online NIPS 2020 What Can Learned Intrinsic Rewards Capture? ICML 2020 Multi-Task Deep Reinforcement Learning with PopArt AAAI 2019 When to use parametric models in reinforcement learning? NIPS 2019 Discovery of Useful Questions as Auxiliary Tasks NIPS 2019 Noisy Networks For Exploration ICLR 2018 Distributed Prioritized Experience Replay ICLR 2018 Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement ICML 2018 The Predictron: End-To-End Learning and Planning ICML 2017 Dueling Network Architectures for Deep Reinforcement Learning ICML 2016 Learning values across many orders of magnitude NIPS 2016