Reinforcement Learning
intermediate

Reinforcement Learning (RL)

Training agents to make sequences of decisions by rewarding desired behaviors.

Detailed Explanation

Reinforcement Learning is an area of machine learning concerned with how software agents ought to take actions in an environment to maximize some notion of cumulative reward. The agent learns by interacting with its environment and receiving rewards or penalties for its actions. Over time, it learns to adopt strategies that maximize its long-term rewards. RL differs from supervised learning in that labeled input/output pairs need not be presented, and sub-optimal actions need not be explicitly corrected.

Examples

  • Game-playing AI like AlphaGo
  • Robotics control systems
  • Recommendation systems

Tags

agents
rewards
environment
policy

Category Information

Reinforcement Learning

Learning through interaction with an environment