Memory-Augmented RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

20 papers9 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Encoding Memory in World Models with Test-Time Model-Based Reinforcement Learning
Nov 6, 2026Maxime Burchi, Fayaz Ali Dharejo, Radu TimofteModel-Based RL Memory-Augmented RL
Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany
ModelBlaster: Closing the Performance Gap through Learning-Augmented Agents Across Models, Kernels and Hardware Backends
Nov 3, 2026Shengjun Kris Dong, Dima Nikiforov, Sahil Modi +4GPU Kernel Optimization Large Language Model-Guided Optimization
NVIDIA · University of California, Berkeley
BLPO: Beyond-Local Policy Optimization for Long-Horizon LLM Agents
Nov 2, 2026Xuanren Chen, Chongyang Tao, Wenpeng Hu +4RL for LLM Agents Long-Horizon LLM Agents
Beihang University · Alibaba Group
RAMA: Retrieval-Augmented Multi-Agent Routing with Episodic Memory for LEO Satellite Networks
Oct 30, 2026Xin Ming Li, Peng HuLEO Satellite Networks Reinforcement Learning
Centre for Computational Mathematics, University of Waterloo, Waterloo, Canada · Dept. of Electrical and Computer Engineering, University of Manitoba, Winnipeg, Canada · Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada
Cheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information
Oct 29, 2026Daniel Strauss, Nikolaos Sotirakis, Zhenshan Bing +1Reinforcement Learning Memory-Augmented RL
Technical University of Munich · Nanjing University · Harbin Institute of Technology
Remember Where You Walk: Learning Spatial Memory for End-to-End Legged Robot Exploration
Oct 27, 2026Leon Magnus, Nico Bohlinger, Jan Peters +1Robotic Spatial Memory Memory-Augmented RL
Technical University of Darmstadt, Germany. · Robotics Institute Germany (RIG). · German Research Center for AI (DFKI).
Memory or a Clock? Auditing a Memory Advantage in XLand-MiniGrid with Seeds, Maps and Evaluation Noise Apart
Oct 24, 2026Rodrigo Reveron-FonsecaReinforcement Learning Memory-Augmented RL
Tecnológico de Monterrey
METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
Oct 22, 2026Ali Najar, Hosein Hasani, Amir Kooshan Fattah +2Meta-Reinforcement Learning Test-Time RL
Department of Computer Engineering Sharif University of Technology
Remember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary Memory
Oct 19, 2026Jiawen Wang, Cheng Xue, Peng Zhang +1Reinforcement Learning In-Context RL
The Australian National University
Value as Memory: Online Value-Guided Post-training for General Robot Policies
Oct 15, 2026Wenye Yu, Yijin Chen, Kaiyi Xiong +7Robotic RL RL Post-Training
Shanghai Jiao Tong University · Shanghai Innovation Institute · Noematrix Ltd.
All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents
Oct 15, 2026Bingbing Wang, Jingjie Lin, Weiming Qiao +2Persistent Memory for Language Models Memory-Augmented Language Model Agents
Harbin Institute of Technology, Shenzhen · The Hong Kong Polytechnic University · Fudan University +1
GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigation
Oct 13, 2026Yousef Liang, Ryan Ardalan, Yarden Goraly +6Memory-Augmented RL Robot Navigation
Stanford University · University of California, Berkeley · NVIDIA
ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning
Sep 30, 2026Oleg Shchendrigin, Egor Cherepanov, Aleksandr I. Panov +1RL Benchmarks Reinforcement Learning
Innopolis University, Innopolis, Russia · MIRIAI, Moscow, Russia · Cognitive AI Systems Lab, Moscow, Russia
Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation
Jul 6, 2026Muhammad Zain Amin, Kibele Sebnem YildirimReinforcement Learning RL for Language Model Reasoning
Department of Software Engineering and IT, ´Ecole de Technologie Sup´erieure, Montreal, Canada · Centre int´egr´e de traumatologie, Hˆopital du Sacr´e-Cœur de Montr´eal, Universit´e de Montr´eal, Montreal, Canada · Desautels Faculty of Management, McGill University, Montreal, Canada.
CORE Planner: Contextual-memory Oriented Reinforcement-learning in Unknown Environments for Robot Navigation
Jun 28, 2026Jintao Kong, Zhihao Zhang, Weihuang Chen +4Reinforcement Learning Robot Navigation
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University
AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning
May 18, 2026Peilin Wu, Xinlu Zhang, Kun Wan +4RL for Language Models Reinforcement Learning
The University of Texas at Dallas · Department of Computer Science, University of California, Santa Barbara · Adobe Inc.
CaMeRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments
May 14, 2026Hong Hong, Feiyu Liao, Yongheng Liang +3RL for Robotics Reinforcement Learning
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China, and the Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China
Writer-R1: Dynamic Rubric Mining for Reinforcement Learning of Open-Ended Writing
Mar 16, 2026Jihao Zhao, Shuaishuai Zu, Zhiyuan Ji +2Memory-Augmented RL RL for Language Models
School of Information, Renmin University of China, Beijing, China · School of Information, BRAIN, Renmin University of China, Beijing, China
Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning
Feb 20, 2026Narjes Nourzad, Carlee Joe-WongMemory-Augmented RL Reinforcement Learning
University of Southern California · Carnegie Mellon University
MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
Feb 20, 2026Narjes Nourzad, Carlee Joe-WongMemory-Augmented RL Reinforcement Learning
University of Southern California, Electrical and Computer Engineering, Los Angeles, CA 90007, USA · Carnegie Mellon University, Electrical and Computer Engineering, Pittsburgh, PA 15213, USA

Nov 6, 2026J/K move · Enter open · S save

Encoding Memory in World Models with Test-Time Model-Based Reinforcement Learning

Maxime Burchi, Fayaz Ali Dharejo, Radu Timofte

Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany

Model-Based RL Memory-Augmented RL

Open paper AskPDF arXiv

Model-based reinforcement learning (MBRL) approaches have demonstrated strong performance across diverse domains in recent years, learning accurate world models from agent trajectories. However, despite this progress, current approaches still struggle to surpass human performance on tasks that require long-term memory and planning. In this work, we address the problem of long-term memory in MBRL by moving beyond the commonly studied paradigm of architecture design. We introduce Test-Time Model-Based Reinforcement Learning (TT-MBRL), using gradient descent at test time to encode the memory of episode observations into world model parameters. This enables the agent to learn a distinct world model for each episode, improving memory capabilities compared to traditional approaches that solely rely on contextual memory. We first establish a proof of concept on a simplified two-dimensional variant of the Memory Maze environment, which we refer to as Memory Maze 2D, showing consistent improvements across different world model architectures. We then demonstrate the effectiveness of TT-MBRL in the 3D domain, achieving new state-of-the-art results on the Memory Maze benchmark. Finally, we show that TT-MBRL maintains strong performance on non-memory benchmarks such as DeepMind Control and Atari 100k.