Transfer Learning in RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

17 papers5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Growing and Transferring Pathways for LLM Reinforcement Learning
Oct 12, 2026Haolin Tian, Yikang Li, Tonghan WangTransfer Learning in RL RL for Language Model Reasoning
Tsinghua University
Selective Transfer of RL Updates for Visual Reasoning
Oct 6, 2026Suxin Ji, Hungtao Wan, Mingjun Liu +1Reinforcement Learning VLM Reasoning
University of Pennsylvania · Independent Researcher · University of Electronic Science and Technology of China +1
Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings
Oct 2, 2026Niklas Emonds, Georgia KoppeTransfer Learning in RL Reinforcement Learning
Hector Institute for AI in Psychiatry (HITKIP) & Department of Psychiatry and Psychotherapy, Central Institute of Mental Health (CIMH), Medical Faculty Mannheim, Heidelberg University · Interdisciplinary Center for Scientific Computing (IWR), Faculty of Mathematics and Computer Science, Heidelberg University · Hertie Institute for AI in Brain Health, University of Tübingen, Germany
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
PhantomEnvironments: Training LLM Agents in Fictional Worlds
Sep 30, 2026Anmol Kabra, Swathi Saravana Selvam, Albert Gong +5Multi-Hop QA Reinforcement Learning
Cornell University · Stanford University
Robust Successor Features
Sep 25, 2026Erik Nikulski, Yamen Habib, Vicenç Gomez +3Reinforcement Learning Generalization in RL
Department of Engineering Universitat Pompeu Fabra
Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints
Jul 19, 2026Hany Hamed, Abhishek Naik, Colin Bellinger +1Domain Randomization Reinforcement Learning
University of Alberta · 3Alberta Machine Intelligence Institute (Amii) · 7Generative Bionics +4
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
Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer
Jun 11, 2026Aryan Naveen, Haitong Ma, Haldun Balim +1RL for Robotics Reinforcement Learning
Massachusetts Institute of Technology · Harvard School of Engineering and Applied Sciences
ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL
Jun 2, 2026Yikang Gui, Bikramjit Banerjee, Prashant DoshiDisentangled Representation Learning Reinforcement Learning
School of Computing, University of Georgia · School of Computing Sciences & Computer Engineering, The University of Southern Mississippi
Task diversity produces systematic transfer but inhibits continual reinforcement learning
May 30, 2026Purab Seth, Neil Shah, Ishaan Sinha +4Transfer Learning Reinforcement Learning
Harvard College · University of Washington · Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University +1
Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach
May 27, 2026Guang-Yuan Hao, Lars van der Laan, Aurélien Bibaut +1Reinforcement Learning Minimax Estimation
Cornell Tech, Cornell University · Netflix Research · Department of Statistics, University of Washington
LANTERN: LLM-Augmented Neurosymbolic Transfer with Experience-Gated Reasoning Networks
May 6, 2026Mahyar Alinejad, Yue Wang, Amrit Singh Bedi +1Reinforcement Learning LLM-Guided RL
Department of Electrical and Computer Engineering, University of Central Florida, Orlando, Florida, USA · Department of Computer Science, University of Central Florida, Orlando, Florida, USA
Predictive Representations for Skill Transfer in Reinforcement Learning
Apr 8, 2026Ruben Vereecken, Luke Dickens, Alessandra RussoTransfer Learning in RL Predictive State Representations
Computer Science, Imperial College, UK · Information Studies, UCL, UK
Energy-Based Transfer for Reinforcement Learning
Jun 19, 2025Zeyun Deng, Jasorsi Ghosh, Fiona Xie +4Transfer Learning in RL Transfer Learning
♠Purdue University · ♢AWS AI · ♣Carnegie Mellon 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
Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
Jul 21, 2024Sheila Schoepp, Mehran Taghian, Shotaro Miwa +3RL Control Reinforcement Learning
Department of Computing Science, University of Alberta, 8900 114 St NW, Edmonton, Alberta, T6G 2S4, Canada · Advanced Technology R&D Center, Mitsubishi Electric Corporation, 8-1-1,Tsukaguchi-honmachi, Amagasaki-shi, Hyogo, 661-8661, Japan · Information Technology R&D Center, Mitsubishi Electric Corporation, 5-1-1, Ofuna, Kamakura-shi, Kanagawa, 247-8501, Japan +1

Oct 12, 2026J/K move · Enter open · S save

Growing and Transferring Pathways for LLM Reinforcement Learning

Haolin Tian, Yikang Li, Tonghan Wang

Tsinghua University

Transfer Learning in RL RL for Language Model Reasoning Reinforcement Learning RL Fine-Tuning Parameter-Efficient Fine-Tuning

Open paper AskPDF arXiv

Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires considerable resources. Reusing the computation acquired through RL across models would extend the value of that training. We propose GrowRL, an RL method that organizes learned updates into compact computational pathways through structural growth. GrowRL freezes the pretrained backbone and adds an independent causal attention branch and a feed-forward network branch at each Transformer layer. Zero-initialized output projections preserve the pretrained policy at initialization, and RL updates only the added pathways. The learned pathways remain explicit after training, allowing transfer to structurally compatible target models and subsequent adaptation with the target backbone frozen. The architecture also supports sequential transfer of additional pathways. By keeping the learned attention and feed-forward computation separate from the pretrained weights, GrowRL provides an explicit structure for preserving and reusing the outcome of an RL run. Experiments across five backbones show competitive mathematical reasoning and out-of-distribution performance with a small number of trainable parameters. Learned pathways provide immediate gains across all three transfer directions, with performance after only 10 target-side updates already close to that after 100 updates in every case. These results support computational pathways as parameter-efficient and reusable units of reinforcement learning adaptation.