Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

Ofir Marom, Benjamin Rosman

Nov-18-2025, 21:43:41 GMT–Neural Information Processing Systems

In this paper we introduce a novel deictic object-oriented framework that has provably efficient learning bounds and can solve a broader range of tasks.

machine learning, object-oriented architecture, transition dynamic, (15 more...)

Neural Information Processing Systems

Nov-18-2025, 21:43:41 GMT

Conferences PDF

Country:
- Africa > South Africa
  - Gauteng
    - Johannesburg (0.04)
    - Pretoria (0.04)
- North America
  - Canada > Quebec
    - Montreal (0.04)
  - United States
    - Massachusetts (0.04)
    - New Jersey > Middlesex County
      - New Brunswick (0.04)

Industry:
- Transportation
  - Ground > Road (0.30)
  - Passenger (0.55)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning (1.00)
  - Representation & Reasoning > Object-Oriented Architecture (0.74)

Duplicate Docs Excel Report

Title
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

Similar Docs Excel Report more

Title	Similarity	Source
None found