Model-Based Reinforcement Learning

Learn about model-based reinforcement learning in detail.

In this lesson, we assume that the agent has a model of the environment, which includes both the knowledge of reward states ρ(s,a)\rho(s,a) and the transfer functions τ(s,a)\tau(s,a). The knowledge of these functions, or a model thereof, is required for model-based RL\text{RL}. The basic challenge in practical applications is to learn these functions from examples of the agent acting in the environment. Here, we are more concerned with showing how to calculate optimal policies if we know these functions.

The basic Bellman equation

Below, we have again the state-action value function:

Get hands-on with 1200+ tech skills courses.