Skip to main content

Deep Reinforcement Learning (DRL) Course by HuggingFace

RL_Basics

What does the Reinforcement Learning Basics image show?​

The image above illustrates the fundamental loop of reinforcement learning (RL):

  • Agent: The learner or decision maker that interacts with the environment.
  • Environment: The world or system with which the agent interacts.
  • Action: At each time step, the agent takes an action based on its current state.
  • State: The environment responds to the action by presenting a new state to the agent.
  • Reward: The environment also provides a reward signal, indicating how good or bad the action was.

Reinforcement Learning Step-by-Step (with Notation)​

At each time step:

  • The agent observes the current state of the environment.
  • Based on current state, the agent selects and performs an action.
  • The environment receives action and transitions to a new state.
  • The environment returns two variables to the agent:
    • The next state
    • A reward, which evaluates the action.

RL_math