Reinforcement learning done with deep neural networks.
Deep RL is like training a video-game dog with treats. It tries a jump, bonks a wall, then learns the level.
You meet it in games and robots. Deep nets help it choose actions after lots of trial and error.
RL
Deep RL adds deep neural networks to the RL setup.
Deep Learning
Deep Learning lets it handle images and other complex input.
DQN
DQN was an early classic method in Deep RL.
ppo
ppo is a common way to train these systems.