- Mastering Atari, Go, chess and shogi by planning with a learned model | Nature https://www.nature.com/articles/s41586-020-03051-4 4 comments artificial
- DeepMind's new MuZero AI has achieved state-of-the-art performance at chess, go, and 57 different Atari games, all without any prior knowledge of the games' rules or dynamics. https://www.nature.com/articles/s41586-020-03051-4 20 comments science
Linking pages
- DeepMind's AI agent MuZero could turbocharge YouTube - BBC News https://www.bbc.com/news/technology-55403473 0 comments
- MuZero Intuition http://www.furidamu.org/blog/2020/12/22/muzero-intuition/ 0 comments
- Reflections on a year studying “Consciousness and AI” | by Arthur Juliani | Dec, 2022 | Medium https://awjuliani.medium.com/reflections-on-a-year-studying-consciousness-and-ai-1b38aa1ef8fb 0 comments
- Reinforcement learning is all you need, for next generation language models. https://yuxili.substack.com/p/reinforcement-learning-is-all-you 0 comments
Linked pages
- OpenAI Five https://blog.openai.com/openai-five/ 272 comments
- GitHub - mgbellemare/Arcade-Learning-Environment: The Arcade Learning Environment (ALE) -- a platform for AI research. https://github.com/mgbellemare/Arcade-Learning-Environment 21 comments
- GitHub - deepmind/open_spiel: OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. https://github.com/deepmind/open_spiel 8 comments
- [1611.05397] Reinforcement Learning with Unsupervised Auxiliary Tasks https://arxiv.org/abs/1611.05397 6 comments
- [1909.11583] Off-Policy Actor-Critic with Shared Experience Replay https://arxiv.org/abs/1909.11583 5 comments
- [1805.11593] Observe and Look Further: Achieving Consistent Performance on Atari https://arxiv.org/abs/1805.11593 4 comments
- [1806.05780] Surprising Negative Results for Generative Adversarial Tree Search https://arxiv.org/abs/1806.05780 4 comments
- [1903.00374] Model-Based Reinforcement Learning for Atari https://arxiv.org/abs/1903.00374 3 comments
- Train and run machine learning models faster | Cloud TPU | Google Cloud https://cloud.google.com/tpu/ 0 comments
Related searches:
Search whole site: site:nature.com
Search title: Mastering Atari, Go, chess and shogi by planning with a learned model | Nature
See how to search.