Shane Legg

16 papers · 2007–2024 · 7 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 ↓

+11 more ↓

🗺️ Taxonomy Completionist (32) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Full 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

📛 The Namer 🌟 Keyword Trendsetter Combo (3) 🏆 Grand Slam 👑 Triple Crown 🧬 Topic Evolution 🏆 Keyword Champion 🧭 Keyword Pioneer 🗃️ Keyword Collector (91) 📈 Trend Setter 🚀 Conference Pioneer 💎 Century Club · Bronze

Venues

NeurIPS (5) ICLR (3) ICML (3) IJCAI (2) AAAI (1) ACL (1) ALT (1)

Top co-authors

Jan Leike (5) Laurent Orseau (4) Grégoire Delétang (3) Miljan Martic (3) Tim Genewein (3) Tom Everitt (2) Anian Ruoss (2) Victoria Krakovna (2) Dario Amodei (2) Rémi Munos (2)

Research topics

Artificial Intelligence (12) Machine Learning (12) Core AI (10) Reinforcement Learning (9) Methods (9) Learning Types · Machine Learning (7) Optimization & Theory (6) Deep Learning (3) Bayesian & Probabilistic (3) Learning Paradigms · Artificial Intelligence (3) Applications (2) Architectures (2) Core Methods (1) Learning Paradigms · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

reward function (5) deep reinforcement learning (3) preference learning (3) reinforcement learning (3) inverse reinforcement learning (3) value of information (2) human preference (2) reward learning (2) q-learning (1) policy optimization (1) temporal difference learning (1) game theory (1) imitation learning (1) attention mechanism (1) sarsa (1) online learning (1) value iteration (1) markov decision process (1) reward modeling (1) ai safety (1)

Papers

Position: Levels of AGI for Operationalizing Progress on the Path to AGI ICML 2024 Neural Networks and the Chomsky Hierarchy ICLR 2023 Randomized Positional Encodings Boost Length Generalization of Transformers ACL 2023 Agent Incentives: A Causal Perspective AAAI 2021 Quantifying Differences in Reward Functions ICLR 2021 Avoiding Side Effects By Considering Future Tasks NeurIPS 2020 Learning Human Objectives by Evaluating Hypothetical Behavior ICML 2020 Meta-trained agents implement Bayes-optimal agents NeurIPS 2020 Pitfalls of Learning a Reward Function Online IJCAI 2020 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ICML 2018 Noisy Networks For Exploration ICLR 2018 Reward learning from human preferences and demonstrations in Atari NeurIPS 2018 Deep Reinforcement Learning from Human Preferences NeurIPS 2017 Reinforcement Learning with a Corrupted Reward Channel IJCAI 2017 Soft-Bayes: Prod for Mixtures of Experts with Log-Loss ALT 2017 Temporal Difference Updating without a Learning Rate NeurIPS 2007