MuZero
MuZero is a reinforcement learning algorithm developed by DeepMind that achieves high performance in games without prior knowledge of their rules by combining model-based and model-free learning.
Free Information Center
MuZero is a reinforcement learning algorithm developed by DeepMind that achieves high performance in games without prior knowledge of their rules by combining model-based and model-free learning.
Dreamer is a model-based reinforcement learning algorithm that combines planning and learning to improve decision-making in complex environments.
AlphaStar is an artificial intelligence program developed by DeepMind to play the real-time strategy game StarCraft II at a professional level. It utilizes deep reinforcement learning and neural networks to master complex strategies and tactics within the game.
AlphaCode is an artificial intelligence system developed to solve competitive programming problems by generating and evaluating potential code solutions. Developed by DeepMind, it uses large-scale language models and ranking algorithms to emulate human-like programming capabilities.
Shane Legg is a computer scientist and entrepreneur known for co-founding DeepMind Technologies, a leading artificial intelligence company acquired by Google. His work focuses on artificial general intelligence and machine learning.
AlphaGo is a computer program developed by DeepMind Technologies to play the board game Go. It was the first AI to defeat a professional human Go player, marking a significant milestone in artificial intelligence research.
Gopher is a large-scale language model developed by DeepMind, designed to advance natural language understanding and generation. It was introduced in late 2021 as part of efforts to create more capable AI systems in natural language processing.
Chinchilla is a language model developed by DeepMind that emphasizes optimized training efficiency through a balanced approach to model size and training data. It represents an advancement in natural language processing by demonstrating improved performance with fewer parameters but more training tokens.
Demis Hassabis is a British artificial intelligence researcher, neuroscientist, and entrepreneur known for co-founding DeepMind, an AI company acquired by Google. His work focuses on combining neuroscience and machine learning to advance artificial general intelligence.