# Dynamic probabilistic logic models for effective abstractions in RL

arXiv: https://arxiv.org/abs/2110.08318 · HTML: https://mlsanity.com/paper/2110.08318/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 9 references that are in the map.
- First posted on arXiv 15 Oct 2021.

## Built on by (most cited first, 1 of 1)

- [Planning with Logical Graph-based Language Model for Instruction Generation](https://mlsanity.com/paper/2308.13782/) (2023)

## Abstract (arXiv)

State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments. Recently, we proposed RePReL (Kokel et al. 2021), a hierarchical framework that leverages a relational planner to provide useful state abstractions for learning. We present a brief overview of this framework and the use of a dynamic probabilistic logic model to design these state abstractions. Our experiments show that RePReL not only achieves better performance and efficient learning on the task at hand but also demonstrates better generalization to unseen tasks.