Zero-Shot Policy Transfer

Follow this topic Ask about this topic

Latest papers

16 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Does a Trading Policy Need to Know What It Trades? Microstructure Invariance and Zero-Shot Transfer of Execution Policies
Nov 5, 2026Hieu Tran, Hong YuZero-Shot Policy Transfer Algorithmic Trading
University of Massachusetts Amherst · University of Massachusetts Lowell
GADAR: Generalizing Across Domains via Action Ranking for Classical Planning
Oct 26, 2026Rajesh Mangannavar, Pranay Dugar, Prasad TadepalliClassical Planning Cross-Domain Generalization
Oregon State University, Corvallis, OR 97330, USA
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
Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation
Sep 30, 2026Morgan Byrd, Jacob Blevins, Maks Sorokin +2Generalization in RL Robot Policy Adaptation
Georgia Institute of Technology, Atlanta, GA, 30308, USA · Georgia Tech Research Institute, Atlanta, GA, 30308, USA
Exploration and Online Transfer with Behavioral Foundation Models
Jun 29, 2026Louis Bagot, Mathieu Lefort, Laëtitia MatignonTransfer Learning in RL RL Exploration
SyCoSMA · Université Lyon 1, CNRS, INSA Lyon LIRIS - UMR5205, 69622 Villeurbanne, France · LIRIS, SyCoSMA, IRISA, MALT, UR +1
Decentralized Autonomous Traffic Management through Corridor Networks
Jun 22, 2026Jasmine Jerry Aloor, Aadarsh Govada, Hamsa BalakrishnanAir Traffic Management Intelligent Transportation Systems
Department of Aeronautics and Astronautics · Massachusetts Institute of Technology · Cambridge, MA, USA +2
Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation
Jun 1, 2026Zhiming Xu, Weitao Zhou, Xianghui Pan +4Robot Policy Adaptation Latent Dynamics Modeling
School of Computer Science and Engineering, Tongji University, Shanghai, China · School of Vehicle and Mobility, Tsinghua University, Beijing, China · Simple AI, Beijing, China +1
Zero-shot adaptation to order book dynamics
May 20, 2026Arip AsadulaevSequential Decision Making Stochastic Optimal Control
Structural Equivalence and Learning Dynamics in Delayed MARL
May 5, 2026Jules Sintes, Ana Bušić, Jiamin ZhuPartially Observable Markov Decision Processes Zero-Shot Policy Transfer
Inria · DIENS, École Normale Supérieure, PSL University · Paris, France +2
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.
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
MorFiC: Fixing Value Miscalibration for Zero-Shot Quadruped Transfer
Mar 15, 2026Prakhar Mishra, Amir Hossain Raj, Xuesu Xiao +1Cross-Embodiment Robot Learning RL for Legged Locomotion
University of Maryland, College Park, MD, USA · George Mason University, Fairfax, VA, USA
Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning
Mar 4, 2026Thomas PravetzRL for Game AI Zero-Shot Policy Transfer
CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety
Feb 26, 2026Umid Suleymanov, Rufiz Bayramov, Suad Gafarli +4Zero-Shot Policy Transfer Language Model Safety Evaluation
Department of Computer Science, Virginia Tech · School of IT and Engineering, ADA University · School of Law, ADA 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

Nov 5, 2026J/K move · Enter open · S save

Does a Trading Policy Need to Know What It Trades? Microstructure Invariance and Zero-Shot Transfer of Execution Policies

Hieu Tran, Hong Yu

University of Massachusetts Amherst · University of Massachusetts Lowell

Zero-Shot Policy Transfer Algorithmic Trading

Open paper AskPDF arXiv

Execution algorithms are calibrated asset by asset, because the queues, trade rates and bid-ask spreads they face differ by orders of magnitude across assets. For reinforcement learning this is zero-shot generalisation across contexts of very different scales, and microstructure invariance proposes a normalisation fixed by theory: measured in each asset's own units of time, size and price, markets look alike. In an exact order-by-order replay of public Nasdaq data, we train policies once, on 954 stocks in 2019, to choose between waiting in the queue and crossing the spread, and evaluate them unchanged on 1,964 unseen stocks in 2020-21, 2,629 stocks in 2025-26, crypto pairs and a second exchange. First, a policy that sees a stock only through its recent trade rate, trade size, spread and price increment (tick) costs within 0.015 spreads per share (a fifth of what learning saves) of a policy whose training data included the stock, and the stock's own history does not help it; it comes within a similar margin of policies trained on the second exchange when every episode counts equally, and within a wider one on crypto. Second, in mean cost before fees, invariant units beat raw units, z-scores and asset descriptors, but by under a basis point: most of their advantage is information and a common cost scale that a learner can also take as plain inputs, and none of the representations tested extrapolates to unseen spread regimes. Third, a near-zero transfer gap to a pooled comparator is weak evidence that a representation is right: we show that such a comparator detects only a small share of what a poor representation loses, and confirm it in synthetic markets and on pendulums.