Policy Learning

Follow this topic Ask about this topic

Momentum

79 papers in the last four weeks, up 316% on the four weeks before. 0.8% of all new papers.

Jul 13Week of Sep 28

Latest papers 416

All topics

Dynamic Latent Routing
May 14, 2026Fangyuan Yu, Xin Su, Amir AbdullahLatent Action Learning RL Post-Training
Thoughtworks AI Labs (TAILS)
Tight Sample Complexity Bounds for Entropic Best Policy Identification
May 13, 2026Amer Essakine, Claire VernadeReinforcement Learning Risk-Sensitive RL
ENS Paris Saclay · University of Technology Nuremberg
Achieving $ε^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions
May 13, 2026Ishaq Hamza, Zaiwei ChenPolicy Gradient Last-Iterate Convergence
IISc · Edwardson School of Industrial Engineering, Purdue University · Purdue IE
GAGPO: Generalized Advantage Grouped Policy Optimization
May 13, 2026Siyuan Zhu, Chao Yu, Rongxin Yang +4Reinforcement Learning Group Relative Policy Optimization
School of Computer Science and Engineering, Sun Yat-sen University · Meituan
ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization
May 12, 2026Nirmal Patel, Fei Wang, Inderjit S. DhillonRL for Language Models Reinforcement Learning
University of Texas at Austin · Google
Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
May 12, 2026Rasool Fakoor, Murdock Aubry, Nicholas Stranges +1Importance Sampling Policy Optimization
Boson AI
TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
May 12, 2026Matthew M. Hong, Jesse Zhang, Anusha Nagabandi +1Robot Policy Adaptation Robot Skill Learning
University of Washington · Amazon FAR
Learning Agentic Policy from Action Guidance
May 12, 2026Yuxiang Ji, Zengbin Wang, Yong Wang +6Agentic RL Reinforcement Learning
1Xiamen University · 2AMAP, Alibaba Group · Work done during internship at AMAP, Alibaba Group +1
Delightful Gradients Accelerate Corner Escape
May 12, 2026Jincheng Mei, Ian OsbandMulti-Armed Bandits Policy Gradient
Google DeepMind
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
May 12, 2026Sijia Li, Yuchen Huang, Zifan Liu +7RL for Language Model Reasoning Credit Assignment in RL
Hong Kong University of Science and Technology · Microsoft Research Asia
Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
May 12, 2026Michael Lu, Max Qiushi Lin, Mo Chen +1Markov Decision Processes Last-Iterate Convergence
Simon Fraser University
Selective Off-Policy Reference Tuning with Plan Guidance
May 12, 2026Duc Anh Le, Tien-Phat Nguyen, Thien Huu Nguyen +2Reinforcement Learning RL for Language Model Reasoning
Independent Author · Hanoi University of Science and Technology, Hanoi, Vietnam · University of Oregon, Eugene, OR, USA +1
Robust Multi-Agent Path Finding under Observation Attacks: A Principled Adversarial-Plus-Smoothing Training Recipe
May 12, 2026Riad AhmedAdversarial Training Adversarial Robustness
University of New Hampshire
Metric-Gradient Projection for Stable Multi-Agent Policy Learning
May 12, 2026Zuyuan Zhang, Sizhe Tang, Mahdi Imani +1Hodge Decomposition Multi-Agent Systems
The George Washington University · Northeastern University
Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance
May 11, 2026Adam Haroon, Erick J. Rodríguez-Seda, Cody Fleming +1RL Control Lyapunov-Based Control
Department of Mechanical Engineering, Iowa State University, Ames, IA, USA · Navy Center for Applied Research in Artificial Intelligence (NCARAI), U.S. Naval Research Laboratory, Washington, D.C., USA · Department of Weapons, Robotics, and Control Engineering, United States Naval Academy, Annapolis, MD, USA
Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$ -step Policy Gradients
May 11, 2026Alex DeWeese, Guannan QuPolicy Gradient Policy Optimization
Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh, PA 15213-3890, USA
Policy Gradient Methods for Non-Markovian Reinforcement Learning
May 11, 2026Avik Kar, Siddharth Chandak, Rahul Singh +4Reinforcement Learning Policy Gradient Methods
Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India. · Department of Electrical Engineering, Stanford University, Stanford, CA, USA. · Department of Electrical and Electronics Engineering, Nanyang Technological University, Singapore. +1
Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework
May 11, 2026Phalguni Nanda, Zaiwei ChenPolicy Gradient Reinforcement Learning
Edwardson School of Industrial Engineering, Purdue University
expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling
May 11, 2026Mingxiong Lin, Zhangquan Gong, Maowen Tang +6Reinforcement Learning KL-Regularized RL
OPPO AI Center
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
May 10, 2026Anish Diwan, Davide Tateo, Christopher E. Mower +3Reinforcement Learning Policy Optimization
Technical University of Darmstadt · Robotics Institute Germany (RIG) · Lund University +3
Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain
May 10, 2026Zhuangyu Han, Abhronil SenguptaEquilibrium Propagation Terrain-Aware Robot Locomotion
School of Electrical Engineering and Computer Science Penn State University University Park, PA 16802
Revisiting Mixture Policies in Entropy-Regularized Actor-Critic
May 9, 2026Jiamin He, Samuel Neumann, Jincheng Mei +2RL Control Policy Optimization
University of Alberta & Amii · Google DeepMind · Canada CIFAR AI Chair
A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets
May 9, 2026Akihiro Kubo, Kosuke Nakanishi, Shin IshiiMulti-Objective Reinforcement Learning Policy Optimization
International Research Center for Neurointelligence, The University of Tokyo, Tokyo, Japan · ATR Neural Information Analysis Laboratories, Kyoto, Japan · Department of Information Science, Kyoto University, Kyoto, Japan
The Reciprocity Gradient
May 8, 2026Yue Lin, Pascal Poupart, Shuhui Zhu +5Credit Assignment in RL Policy Gradient Methods
The Chinese University of Hong Kong, Shenzhen · LIGHTSPEED · University of Waterloo +2
KL for a KL: On-Policy Distillation with Control Variate Baseline
May 8, 2026Minjae Oh, Sangjun Song, Gyubin Choi +2Language Model Distillation Policy Gradient Methods
Graduate School of Data Science Seoul National University
Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
May 8, 2026Rahaf Abu Hara, Vaibbhav Murarri, Claudio ZitoPolicy Optimization LLM-Guided RL
Laboratory of AI and Robotics Research (LAIRR) Heriot-Watt University Dubai, United Arab Emirates
Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
May 8, 2026Juil Koo, Mingue Park, Jiwon Choi +2Robot Policy Learning Wasserstein Gradient Flows
KAIST
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
May 8, 2026Yunho Choi, Jongwon Lim, Woojin Ahn +3Value Function Estimation RL for Language Model Reasoning
Graduate School of Data Science Seoul National University · Computer Science and Engineering Seoul National University
Towards Differentially Private Reinforcement Learning with General Function Approximation
May 7, 2026Yi He, Xingyu ZhouRegret Minimization in RL Reinforcement Learning
Wayne State University, Detroit, USA
Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents
May 7, 2026Shirin Sohrabi, Haritha Ananthakrishnan, Harsha Kokel +2LLM Agent Skill Learning Policy Learning
IBM

May 14, 2026, cs.LGJ/K move · Enter open · S save

Dynamic Latent Routing

Fangyuan Yu, Xin Su, Amir Abdullah

Thoughtworks AI Labs (TAILS)

Latent Action Learning RL Post-Training Policy Learning

Open paper AskPDF arXiv

We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be recovered through temporal composition of intermediate optimal sub-policies. Motivated by the "search, select, update" principle underlying GDS, we propose Dynamic Latent Routing (DLR), a language-model post-training method that jointly learns discrete latent codes, routing policies, and model parameters through dynamic search in a single training stage. In low-data fine-tuning settings, DLR matches or outperforms supervised fine-tuning across four datasets and six models, achieving a mean gain of +6.6 percentage points, while prior discrete-latent baselines consistently underperform SFT. Mechanistic analyses and targeted code ablations show that DLR learns structured routing behaviors with distinct causal roles.

Momentum

Related topics

Latest papers 416