Reinforcement Learning is a field of machine learning where an agent learns to make optimal decisions in an environment based on maximizing the expected cumulative reward.
Formally, RL is often modeled by Markov Decision Processes (MDP), defined by state space, action space, transition probabilities, and reward function.
The central task is to find a policy π(s) that maximizes the expected return, using methods such as value iteration, policy iteration, Monte Carlo methods, and temporal-difference learning (e.g., Q-learning, SARSA).
Modern approaches like deep reinforcement learning combine neural networks with RL algorithms to learn in complex, high-dimensional environments.
Definition:
Reinforcement Learning is a learning paradigm where an agent learns a policy through interaction with an environment that maximizes cumulative reward, typically modeled as a Markov decision process.
Source:
Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction. MIT Press.