Agent57
Agent57 is a model-free distributed reinforcement learning algorithm developed by Google DeepMind and reported in 2020.
Google DeepMind
Explore Google DeepMind through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: AI in Gaming
Articles that also belong to these categories. Counts cover all of Google DeepMind.
All articles (106)AI Models (32)Large Language Models (26)Multimodal AI (21)AI for Science (18)Generative AI (17)Reinforcement Learning (12)Open Source AI (8)People (8)Google (6)Robotics (6)AI Agents (5)AI in Gaming (5)Deep Learning (5)Diffusion Models (5)Drug Discovery (5)Embodied AI (5)Healthcare AI (5)Image Generation (5)Mathematics (5)Reasoning Models (5)Video Generation (5)AI Research (4)Artificial Intelligence (4)Small Language Models (4)AI Benchmarks (3)Music & Audio Generation (3)Speech & Audio AI (3)World Models (3)AI Code Generation (2)AI Hardware (2)AI Safety (2)Computer Vision (2)Natural Language Processing (2)Neural Networks (2)AI Alignment (1)AI Companies (1)AI in Cybersecurity (1)Algorithms (1)Conversational AI (1)Data & Datasets (1)Microsoft (1)Mixture of Experts (1)Model Architecture (1)Model Evaluation (1)Training & Optimization (1)Transformer Models (1)
Showing 1-5 of 5 articles
AlphaGo Zero
AlphaGo Zero is a Go-playing computer program developed by DeepMind that reached a superhuman level entirely through self-play reinforcement learning, starting from random play with no human game data.
AlphaStar
AlphaStar is an artificial intelligence system built by Google DeepMind that in 2019 became the first AI to reach Grandmaster level in the real-time strategy game StarCraft II
AlphaZero
AlphaZero is a general-purpose reinforcement learning algorithm developed by DeepMind that taught itself to play chess, shogi (Japanese chess), and Go at a superhuman level from scratch, using only the rules…
SIMA (DeepMind)
SIMA (Scalable Instructable Multiworld Agent) is a family of generalist embodied AI agents developed by Google DeepMind that follow free-form natural-language instructions to act in a wide range of…