Learning human objectives by evaluating hypothetical behaviours
News
Discover our latest AI breakthroughs, projects, and updates
From unlikely start-up to major scientific organisation: Entering our tenth year at DeepMind
Advanced machine learning helps Play Store users discover personalised apps
AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning
Restoring ancient text using deep learning: a case study on Greek epigraphy
Causal Bayesian Networks: A flexible tool to enable fairer machine learning
DeepMind’s health team joins Google Health
The Podcast: Episode 8: Demis Hassabis - The interview
The Podcast: Episode 7: Towards the future
Replay in biological and artificial neural networks
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
The Podcast: Episode 6: AI for everyone
The Podcast: Episode 5: Out of the lab
The Podcast: Episode 4: AI, Robot
The Podcast: Episode 3: Life is like a game
The Podcast: Episode 2: Go to Zero
The Podcast: Episode 1: AI and neuroscience - The virtuous circle
Welcome to the DeepMind podcast
Using machine learning to accelerate ecological research
Using AI to give doctors a 48-hour head start on life-threatening illness
How evolutionary selection can train more capable self-driving cars
Unsupervised learning: The curious pupil
Capture the Flag: the emergence of complex cooperative agents
Identifying and eliminating bugs in learned predictive models
