Model-Free

Follow this topic Ask about this topic

Momentum

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

Jul 6Week of Sep 21

Latest papers 18

All topics

Q-Learning for Reachability in MEC-Free MDPs
Oct 1, 2026Lu-Chin Chang, Suguman BansalQ-Learning Markov Decision Processes
Georgia Institute of Technology
Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits
Sep 29, 2026Gaurav Agarwal, Ashish Garg, Isha SinghalTime-To-First-Token Graphics Processing Unit Resources
Separating perception from reasoning in vision-language models: a model-free render ceiling for crystal structures
Sep 1, 2026Can Polat, Mustafa Kurban, Erchin Serpedin +1Recent Vision-Language Models Ceiling
Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA · Department of Electrical and Computer Engineering, Texas A&M University at Qatar, Doha, Qatar · Department of Prosthetics and Orthotics, Ankara University, Ankara, Turkey +1
Energy-Optimal Spatial Iterative Learning within a Virtual Tube
Jun 30, 2026Chen Min, Shuli Lv, Pengda Mao +3Unmanned Aerial Vehicle Trajectories Energy-Efficient
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China · Tianmushan Laboratory, Beihang University, Hangzhou, 311115
Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data
Jun 25, 2026Erhan Bayraktar, Martin Hernandez, Qinxin Yan +1Stochastic Optimal Control Model-Free
Department of Mathematics, University of Michigan, Ann Arbor, MI, USA. · Department of Statistics and Data Science, University of California, Los Angeles, CA, USA. · Program in Applied and Computational Mathematics, Princeton University, Princeton, NJ, USA.
Model-Free Reinforcement Learning Control for Resilient Cyber-Physical Systems
Jun 17, 2026Hugo O. Garcés, Alejandro J. Rojas, Bernardo A. Hernández +5Cyber-Physical System Model-Free Reinforcement Learning
Departamento de Ingeniería Informática y Ciencias de la Computación, Universidad de Concepción, Concepción, Chile · Electrical Engineering Departament, Universidad de Talca · Department of Electrical & Computer Engineering, University of Alberta, Edmonton, T6G 1H9, Alberta, AB, Canada +2
Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process
Jun 15, 2026Jongmin Lee, Ernest K. Ryu, Vaneet AggarwalMarkov Decision Processes Model-Free
Seoul National University · UCLA · Purdue University
A Hybrid Model-Based and Model-Free Framework for Active Multi-View Viewpoint Optimization in Sonar Target Recognition
Jun 13, 2026Yongkyoon Park, Jane ShinForward-Looking Sonar Multi-View
University of Florida Gainesville, FL, United States of America
AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding
Jun 4, 2026Runheng Liu, Jincheng Xie, Wen Hu +2Speculative Decoding Drafts
School of Computer Science and Technology, Beijing Institute of Technology · Department of Mathematical Sciences, Tsinghua University · JDT AI Infra
Cortex and subcortex play distinct roles over learning when cortical memory is limited
May 30, 2026Matthew Farrell, Taro ToyoizumiHuman Visual Cortex Working Memory
Laboratory for Neural Computation and Adaptation RIKEN Center for Brain Science, Wako, Japan · Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan.
Transfer Learning for Customized Car Racing Environments
May 18, 2026Benedict Florance Arockiaraj, Richard Chang, Wesley YeeTransfer Learning Autonomous Racing
SEAS
Towards Model-Free Learning in Dynamic Population Games: An Application to Karma Economies
May 11, 2026Matteo Cederle, Saverio Bolognani, Gian Antonio SustoDeep Q-Networks Model-Free
Department of Information Engineering University of Padova · Automatic Control Laboratory ETH Zurich
Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL
May 8, 2026Shengbo Wang, Zexi ZhangDistributional Reinforcement Learning Large Deviation Principle
Daniel J. Epstein Department of Industrial and Systems Engineering, University of Southern California
Actor-Critic Algorithm for Dynamic Expectile and CVaR
May 8, 2026Yudong Luo, Erick DelageConditional-Value-At-Risk Soft Actor-Critic
1GERAD & Department of Decision Sciences, HEC Montr´eal, Canada · 2Mila - Quebec AI Institute, Canada
Model-Free Inference of Investor Preferences: A Relative Entropy IRL Approach
Apr 27, 2026Chen XuReward Functions Model-Free
Department of Engineering, Shenzhen MSU-BIT University. Address: 1 International University Park Road, Longgang District, Shenzhen, Guangdong, China.
A Model-Free Universal AI
Feb 26, 2026Yegon Kim, Juho LeeModel-Free Offline Reinforcement Learning
Graduate School of AI, KAIST, Seoul, South Korea
Policy Gradient with Self-Attention for Model-Free Distributed Nonlinear Multi-Agent Games
Sep 22, 2025Eduardo Sebastián, Maitrayee Keskar, Eeman Iqbal +3Multi-Agent Reinforcement Learning Policy Gradient
Department of Computer Science and Technology, University of Cambridge, UK · Department of Electrical and Computer Engineering, University of California San Diego, USA · RoPeRt group, at DIIS - I3A, Universidad de Zaragoza, Spain
Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis
May 18, 2025Zachary Roch, George Atia, Yue WangModel-Free Offline Reinforcement Learning
Department of Electrical and Computer Engineering, University of Central Florida, Orlando, Florida, USA. · Department of Computer Science, University of Central Florida, Orlando, Florida, USA.

Oct 1, 2026, cs.AIJ/K move · Enter open · S save

Q-Learning for Reachability in MEC-Free MDPs

Lu-Chin Chang, Suguman Bansal

Georgia Institute of Technology

Q-Learning Markov Decision Processes Reachability Model-Free Offline Reinforcement Learning

Open paper AskPDF arXiv

Reinforcement learning (RL) for reachability specifications is fundamental to sequential decision-making. Prior work establishes asymptotic convergence to optimal policies, but only through model-based methods that must explicitly estimate the transition probabilities of the underlying Markov Decision Process (MDP). We present Quasar, the first model-free algorithm with asymptotic guarantees for reachability on the fragment of MDPs free of non-terminal maximal end components (MECs), a building block to which every MDP reduces by the standard MEC quotient. Our algorithm follows the classical Q-learning approach, using temporal-difference updates to converge to an optimal policy without ever learning the transition probabilities. The resulting learner reduces the memory footprint from the O(|S|^2|A|) that model-based methods require to O(|S||A|). On the standardized Quantitative Verification Benchmark Set, our algorithm converges to the optimal policy with orders of magnitude fewer samples than the previous model-based state-of-the-art. Together these results are a concrete step toward the practical deployment of reachability learning and, with it, of specification-guided RL.

Momentum

Related topics

Latest papers 18