Zero-Shot RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

17 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations
Oct 9, 2026Duaa Nakshbandi, Zhiyu An, Wan DuZero-Shot RL Reinforcement Learning
University of California, Merced
Task Inference Beyond Least Squares in Behavioral Foundation Models
Oct 4, 2026Kuan-Hsun Tu, Chien-Sheng Chiang, Hsin-Wei Chen +2Reinforcement Learning Multi-Task RL
National Taiwan University
Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation
Sep 30, 2026Morgan Byrd, Jacob Blevins, Maks Sorokin +2Robot Policy Learning Robot Policy Adaptation
Georgia Institute of Technology, Atlanta, GA, 30308, USA · Georgia Tech Research Institute, Atlanta, GA, 30308, USA
Towards Zero-Shot Task Transfer with Neurosymbolic World Models
Aug 18, 2026Isidoro Tamassia, Lennert De Smet, Giuseppe MarraZero-Shot RL World Model Learning
KU Leuven, Department of Computer Science, Belgium
Exploration and Online Transfer with Behavioral Foundation Models
Jun 29, 2026Louis Bagot, Mathieu Lefort, Laëtitia MatignonReinforcement Learning RL Exploration
SyCoSMA · Université Lyon 1, CNRS, INSA Lyon LIRIS - UMR5205, 69622 Villeurbanne, France · LIRIS, SyCoSMA, IRISA, MALT, UR +1
Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning
May 13, 2026Stefan Stojanovic, Alexandre ProutiereRepresentation Learning Reinforcement Learning
KTH, Stockholm, Sweden · KTH, Digital Futures, Stockholm, Sweden
Improving Zero-Shot Offline RL via Behavioral Task Sampling
Apr 28, 2026Nazim Bendib, Nicolas Perrin-Gilbert, Olivier SigaudZero-Shot RL Offline RL
Institut des Systèmes Intelligents et de Robotique, ISIR, Sorbonne Université, Paris, France.
Safety Guarantees in Zero-Shot Reinforcement Learning for Cascade Dynamical Systems
Apr 12, 2026Shima Rabiei, Sandipan Mishra, Santiago PaternainZero-Shot RL Safe RL
The authors are with the Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute. · The author is with the Department of Mechanical, Aerospace and Nuclear Engineering, Rensselaer Polytechnic Institute.
ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
Apr 9, 2026Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu RanaZero-Shot RL Zero-Shot Policy Transfer
Applied Artificial Intelligence Initiative, Deakin University, Waurn Ponds, Geelong · School of IT, Deakin University, Waurn Ponds, Geelong
Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning
Mar 26, 2026Jiajun Hu, Nuria Armengol Urpi, Jin Cheng +1Zero-Shot RL Reinforcement Learning
Department of Mechanical Engineering, EPFL · Department of Computer Science, ETH Zurich · Max Planck Institute for Intelligent Systems
Unified Policy Value Decomposition for Rapid Adaptation
Mar 18, 2026Cristiano Capone, Luca Falorsi, Andrea Ciardiello +1Zero-Shot RL Reinforcement Learning
Computational Neuroscience Unit, Istituto Superiore di Sanit`a, 00161, Rome, Italy · Ospedale Santa Lucia, Rome, Italy · School of Computer Science, University of Sheffield,Sheffield,S10 2TN, United Kingdom
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
Mar 16, 2026Pranaya Jajoo, Harshit Sikchi, Siddhant Agarwal +3Behavioral Foundation Models Zero-Shot RL
Department of Computing Science, University of Alberta, Canada · Alberta Machine Intelligence Institute (Amii) · The University of Texas at Austin +2
Contextual Intelligence The Next Leap for Reinforcement Learning
Feb 17, 2026André BiedenkappContextual RL Zero-Shot RL
Albert-Ludwigs-Universität Freiburg, Germany
Can We Really Learn One Representation to Optimize All Rewards?
Feb 11, 2026Chongyi Zheng, Royina Karegoudra Jayanth, Benjamin EysenbachZero-Shot RL Representation Learning
Princeton University
A Unified Framework for Zero-Shot Reinforcement Learning
Oct 23, 2025Jacopo Di Ventura, Jan Felix Kleuker, Aske Plaat +1Zero-Shot RL Formal Methods for RL
Leiden University
MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer
Jun 2, 2025Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu RanaReinforcement Learning Transfer Learning
Applied Artificial Intelligence Initiative, Deakin University · School of IT, Deakin University
Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs
Oct 4, 2024Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan +1Reinforcement Learning RL Exploration
Delft University of Technology, Delft, The Netherlands

Oct 9, 2026J/K move · Enter open · S save

Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations

Duaa Nakshbandi, Zhiyu An, Wan Du

University of California, Merced

Zero-Shot RL Reinforcement Learning Zero-Shot Policy Transfer Representation Learning for RL

Open paper AskPDF arXiv

Successor-feature-based zero-shot reinforcement learning methods pre-train a task encoder and successor-feature predictor on offline, reward-free data, then recover a policy at test time by solving a closed-form linear regression over a small labeled dataset. We identify an underexplored limitation of this approach: when the task encoder produces dense representations, the inferred reward signal becomes diffuse across the state space, reducing the contrast between goal-relevant states and the background and providing a weaker signal for the policy to follow. We address this limitation by introducing an l1 sparsity penalty that concentrates reward-predictive structure into a smaller effective subspace of the task encoder's latent space. The penalty is applied only during training and requires no architectural change or modification to the closed-form inference procedure. We instantiate this approach as Sparse-TD-JEPA, a single-line of code addition based on Temporal-Difference Joint-Embedding Predictive Architecture (TD-JEPA) that significantly improved its performance in zero-shot reinforcement learning. We evaluate Sparse-TD-JEPA on 65 tasks across the DeepMind Control (DMC) Suite and OGBench, covering locomotion, navigation, trajectory stitching, puzzle solving, and robotic manipulation. Sparse-TD-JEPA improves over TD-JEPA in all 13 domain-level comparisons. On DMC, it increases the average return from 661 +- 6 to 714 +- 3. On OGBench, it increases the average success rate from 38.0 +- 0.8 to 48.4 +- 2.3, with improvements of 13.4-18.0 percentage points on the evaluated antmaze navigation and stitching domains. Overall, Sparse-TD-JEPA achieves the highest mean performance among established zero-shot baselines in nine of the 13 domains. Analysis further shows that sparsity produces a sharper and more task-informative inferred reward landscape.