Shane Legg
Google DeepMind (United Kingdom) · 96 works · 34,781 citations · h-index 26
Top works
- Human-level control through deep reinforcement learning
- Massively Parallel Methods for Deep Reinforcement Learning
- Universal Intelligence: A Definition of Machine Intelligence
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Deep reinforcement learning from human preferences
- Noisy Networks for Exploration
- A Collection of Definitions of Intelligence
- Machine super intelligence
- AI Safety Gridworlds
- A Formal Measure of Machine Intelligence
- DeepMind Lab
- Reinforcement Learning with a Corrupted Reward Channel
- Scalable agent alignment via reward modeling: a research direction
- Reward learning from human preferences and demonstrations in Atari
- Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response
- An Approximation of the Universal Intelligence Measure
- An Approximation of the Universal Intelligence Measure
- Dynamic Portfolio Choice and Asset Pricing with Narrow Framing and Probability Weighting
- An MDL estimate of the significance of rules
- A Universal Measure of Intelligence for Artificial Agents.