Hado P. van Hasselt
Google DeepMind (United Kingdom)
1 paper in the Anchorcite directory, published in 2016, cited 6,775 times in total.
Research topics
- Reinforcement Learning in Robotics · 1 paper
- Advanced Bandit Algorithms Research · 1 paper
- Artificial Intelligence in Games · 1 paper
Frequent co-authors
- Arthur Guez · 1 paper
- David Silver · 1 paper
Papers
- Deep Reinforcement Learning with Double Q-LearningAAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · 2016 · 6,775 citations
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we…
Metadata from OpenAlex (CC0).