Deep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning.

Overview · History · Algorithms · Research

Reinforcement learning (RL) is an interdisciplinary area of machine learning and optimal control concerned with how an intelligent agent ought to take ...

Deep · Q-learning · Temporal difference learning · Markov decision process

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the ...

Reinforcement learning · Influence of variables · Variants

Deep learning is the subset of machine learning methods based on neural networks with representation learning. The adjective "deep" refers to the use of ...

Comparison · Feature learning · Deep belief network · Transformer architecture

In machine learning, reinforcement learning from human feedback (RLHF) is a technique to align an intelligent agent to human preferences.