# Deep Sets for Generalization in RL

arXiv: https://arxiv.org/abs/2003.09443 · HTML: https://mlsanity.com/paper/2003.09443/

## Key facts

- Cited by 3 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 20 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [Policy Architectures for Compositional Generalization in Control](https://mlsanity.com/paper/2203.05960/) (2022)
- [Set-to-Sequence Methods in Machine Learning: a Review](https://mlsanity.com/paper/2103.09656/) (2021)
- [Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents](https://mlsanity.com/paper/2202.05129/) (2022)

## Abstract (arXiv)

This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise permutation invariant networks inspired from Deep Sets and gated-attention mechanisms. In a 2D procedurally-generated world where agents targeting goals in natural language navigate and interact with objects, we show that these architectures demonstrate strong generalization capacities to out-of-distribution goals. We study the generalization to varying numbers of objects at test time and further extend the object-centered architectures to goals involving relational reasoning.