Reinforcement Learning

machine-learning

Definition

Reinforcement Learning

Reinforcement learning is a paradigm of machine learning where an autonomous agent learns to make decisions by interacting with an environment to maximise a cumulative reward signal. Formally, the problem is modelled as a Markov Decision Process defined by .

Formalism

The learning environment is defined by the state space and action space , with transition probabilities and an immediate reward function . The learner’s objective is to identify an optimal policy that maximises the expected discounted return , where is the discount factor.