# Fitted Q-Learning for Relational Domains

arXiv: https://arxiv.org/abs/2006.05595 · HTML: https://mlsanity.com/paper/2006.05595/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2020.

## Built on by (most cited first, 7 of 7)

- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Explainability in reinforcement learning: perspective and position](https://mlsanity.com/paper/2203.11547/) (2022)
- [Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems](https://mlsanity.com/paper/2204.12665/) (2022)
- [Egocentric Planning for Scalable Embodied Task Achievement](https://mlsanity.com/paper/2306.01295/) (2023)
- [Knowledge Infused Policy Gradients for Adaptive Pandemic Control](https://mlsanity.com/paper/2102.06245/) (2021)
- [Human-Allied Relational Reinforcement Learning](https://mlsanity.com/paper/2510.16188/) (2025)
- [Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains](https://mlsanity.com/paper/2502.19297/) (2025)

## Abstract (arXiv)

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.