Skip to Main content Skip to Navigation
Conference papers

Deep Sets for Generalization in RL

Tristan Karch 1 Cédric Colas 1 Laetitia Teodorescu 1 Clément Moulin-Frier 1 Pierre-Yves Oudeyer 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : 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.
Document type :
Conference papers
Complete list of metadata
Contributor : Tristan Karch Connect in order to contact the contributor
Submitted on : Tuesday, January 26, 2021 - 12:13:36 PM
Last modification on : Friday, January 21, 2022 - 3:08:51 AM
Long-term archiving on: : Tuesday, April 27, 2021 - 6:12:45 PM


Files produced by the author(s)


  • HAL Id : hal-03120669, version 1
  • ARXIV : 2003.09443



Tristan Karch, Cédric Colas, Laetitia Teodorescu, Clément Moulin-Frier, Pierre-Yves Oudeyer. Deep Sets for Generalization in RL. Beyond Tabula Rasa in Reinforcement Learning: agents that remember adapt and generalize, Workshop at ICLR, Apr 2021, Addis Ababa, Ethiopia. ⟨hal-03120669⟩



Les métriques sont temporairement indisponibles