Landmark 2 stops to get here · leads to 3

Agent

In RL, the learner or decision-maker that takes actions in an environment to maximize cumulative reward.

Your route here

2 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Reinforcement Learning ✓ understood

    Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies.

  3. Agent · you are here ✓ understood

Picture it

Observe stateWhat the environment looks like…Choose actionPicked by the agent's policyEnvironment respondsThe world changesReceive rewardPlus the next stateUpdate policyLearn from the outcomeMaximize total reward
  1. 01 Observe state What the environment looks like now
  2. 02 Choose action Picked by the agent's policy
  3. 03 Environment responds The world changes
  4. 04 Receive reward Plus the next state
  5. 05 Update policy Learn from the outcome

↺ back to 01 · Maximize total reward

Each pass through the loop, the agent acts, sees the reward, and adjusts its policy toward higher cumulative reward.

Where it sits

Before this

Reinforcement Learning
Agent

Leads to

Policy Environment Multi-Agent RL

Explore nearby

Agents & RL AI Agent A system where a large language model decides its own next steps in a loop: calling tools, reading the results, and continuing until the task is done. Agents & RL Environment In RL, the world the agent interacts with, providing states, accepting actions, and returning rewards. Agents & RL Policy A strategy or mapping from states to actions that defines the agent's behavior in reinforcement learning. Agents & RL Reward A scalar feedback signal indicating how good an action was, used to train reinforcement learning agents. Agents & RL Tool Use LLMs learning to call external tools, APIs, or functions to extend capabilities beyond text generation (calculators, search, code execution). Agents & RL Multi-Agent RL Reinforcement learning with multiple agents that interact and potentially cooperate or compete.