Mastering the game of Go with deep neural networks and tree search

By Thomas Mülleder. 2019

Subfields: Reinforcement Learning, Game & Decision Theory

Citations in the corpus

• Towards Evaluating the Robustness of Neural Networks (2016, neutral): “They are also used for speech recognition [18], natural language processing [1], and playing games [43], [32].”
• Relational inductive biases, deep learning, and graph networks (2018, neutral): “, 2015), to game play (Mnih et al., 2015; Silver et al., 2016; Moravč́ık et al., 2017), are a testament to this minimalist principle.”
• Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies (2018, neutral): “While current methods are able to outperform humans on many individual problems [52, 36, 20], these algorithms suffer from catastrophic forgetting [14, 33, 34, 42, 17].”
• Challenges of Real-World Reinforcement Learning (2019, neutral): “Other rollout-based approaches like AlphaGo (Silver et al., 2016) will improve with more rollouts, but are not engineered to run at a specific frequency.”