Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Ofir Marom, Benjamin Rosman
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use deictic instead of propositional representation as passengers increase | DOORMAX OO-MDP learner · All-passenger any-destination Taxi | average test steps | Improved |
| transfer previously learned transition dynamics when increasing passengers n (ablation) | Deictic OO-MDP · Taxi, n = 4 | average test steps | Improved |
| no transfer (relearn dynamics for each n) (ablation) | Deictic OO-MDP · Taxi, n = 4 to n = 5 larger gridworld | steps relative to optimal | Hurt |
| zero-shot transfer dynamics from toy Sokoban MDP to large Sokoban task | Deictic OO-MDP · Sokoban Micro-Cosmos | steps to solve: 209 | Improved |
Closest papers by meaning
- Zero-Shot Reinforcement Learning via Function Encoders (ICML 2024 · similarity 0.89)
- QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning (ICML 2024 · similarity 0.88)
- Zero-Shot Offline Imitation Learning via Optimal Transport (ICML 2025 · similarity 0.86)
- Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings (ICML 2024 · similarity 0.86)
- Towards Robust Zero-Shot Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Proto Successor Measure: Representing the Behavior Space of an RL Agent (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
