DeepAI AI Chat
Log In Sign Up

Fitted Q-Learning for Relational Domains

by   Srijita Das, et al.
Duke University
Technische Universität Darmstadt
The University of Texas at Dallas

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.


page 1

page 2

page 3

page 4


Learning Relational Representations with Auto-encoding Logic Programs

Deep learning methods capable of handling relational data have prolifera...

Automatic Induction of Bellman-Error Features for Probabilistic Planning

Domain-specific features are important in representing problem structure...

Exploiting First-Order Regression in Inductive Policy Selection

We consider the problem of computing optimal generalised policies for re...

A Geometric-Relational Deep Learning Framework for BIM Object Classification

Interoperability issue is a significant problem in Building Information ...

Probabilistic Relational Planning with First Order Decision Diagrams

Dynamic programming algorithms have been successfully applied to proposi...

Relational Algorithms for k-means Clustering

The majority of learning tasks faced by data scientists involve relation...

Clustered Relational Thread-Modular Abstract Interpretation with Local Traces

We construct novel thread-modular analyses that track relational informa...