Fitted Q-Learning for Relational Domains

Understand

We consider the problem of Approximate Dynamic Programming in relational domains.

• Inspired by the success of fitted Q-learning methods in propositional settings, we develop the first relational fitted Q-learning algorithms by representing the value function and Bellman residuals.
• When we fit the Q-functions, we show how the two steps of Bellman operator; application and projection steps can be performed using a gradient-boosting technique.
• Our proposed framework performs reasonably well on standard domains without using domain models and using fewer training trajectories.