Research & Science

Reinforcement Learning

Agents that learn from rewards, from games to robotics.

3 stories RSS

DQN explained: the paper that taught an AI to play Atari from pixels

DeepMind's deep Q-network learned dozens of Atari games from raw screen pixels and scores alone. How Q-learning, experience replay and target networks made it work.

AI DeskOct 183 min read

Reinforcement LearningResearch

PPO explained: the reinforcement learning algorithm behind RLHF

Proximal Policy Optimization made policy-gradient training simpler and more stable by limiting how far each update can move. How it works and why it is everywhere.

AI DeskOct 183 min read

Gaming

How AI is changing video games: development, NPCs and players

From AlphaStar to AI-powered characters and generative assets: how AI is used to play, make and personalize games, and why it is controversial with game workers.

AI DeskOct 183 min read