Key papers

• Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning (2026)
  Zhenyu Hou et al.
  10.35
• Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents (2026)
  Changdae Oh et al.
  8.17
• PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data (2025)
  Aishwarya Mandyam et al.
  4.93
• Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL (2026)
  Jongchan Park et al.
  4.39
• Loss Smoothing for Stable Adaptation Under Distribution Shift (2026)
  Darshan Patil et al.
  4.39
• Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows (2026)
  Karthikeya Aditya Vissa et al.
  4.39
• Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF (2026)
  Eric Zhu et al.
  4.39
• When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? (2026)
  Xuanfei Ren et al.
  4.33
• Reinforcement Learning Foundation Models Should Already Be A Thing (2026)
  Abdelrahman Zighem et al.
  4.33
• Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning (2026)
  Xiaoyue Xu et al.
  4.33
• Forecasting what Matters: Decision-Focused RL for Controlled EV Charging with Unknown Departure Times (2026)
  Giuseppe Gabriele et al.
  4.33
• Weight-Space Geometry of Offline Reasoning Training (2026)
  Aleksandr Nikolich et al.
  4.33
• Offline Reinforcement Learning for Warehouse SLAM Throughput Control (2026)
  Tina Dongxu Li et al.
  4.33
• Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models (2026)
  Thibaut Kulak
  4.33
• Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors (2026)
  Guozheng Ma et al.
  4.33
• RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization (2025)
  Kai Fukazawa et al.
  2.56
• Task-guided IRL In Pomdps That Scales (2022)
  Franck Djeumou, Christian Ellis, Murat Cubuktepe, et al.
  2.26
• Beyond Pessimism: Offline Learning in KL-regularized Games (2026)
  Yuheng Zhang et al.
  1.83
• Long-horizon Rollout Via Dynamics Diffusion For Offline Reinforcement Learning (2024)
  Hanye Zhao, Xiaoshen Han, Zhengbang Zhu, et al.
  1.81
• StagePilot: A Deep Reinforcement Learning Agent for Stage-Controlled Cybergrooming Simulation (2026)
  Heajun An et al.
  1.72
• On the Role of Computation in Reinforcement Learning (2026)
  Raj Ghugare et al.
  1.72
• Resource-Conscious RL Algorithms for Deep Brain Stimulation (2026)
  Arkaprava Gupta et al.
  1.67
• Safe Exploration via Policy Priors (2026)
  Manuel Wendl et al.
  1.67
• Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach (2025)
  Sebastian Reboul and H\'el\`ene Halconruy and Randal Douc
  1.50
• Revisiting Actor-Critic Methods in Discrete Action Off-Policy Reinforcement Learning (2025)
  Reza Asad et al.
  1.44
• Failure Modes of Maximum Entropy RLHF (2025)
  \"Omer Veysel \c{C}a\u{g}atan and Bar{\i}\c{s} Akg\"un
  1.44
• OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction (2025)
  Lujie Yang et al.
  1.44
• Offline Behavioral Data Selection (2025)
  Shiye Lei, Zhihao Cheng, Dacheng Tao
  1.28
• Offline Critic-guided Diffusion Policy For Multi-user Delay-constrained Scheduling (2025)
  Zhuoran Li, Ruishuo Chen, Hai Zhong, et al.
  1.28
• Horizon Reduction As Information Loss In Offline Reinforcement Learning (2025)
  Uday Kumar Nidadala, Venkata Bhumika Guthi
  1.28
• One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion (2025)
  Yahao Fan et al.
  1.22
• Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data (2025)
  Yi Zhao et al.
  1.06
• Federated Offline Policy Learning (2023)
  Aldo Gael Carranza, Susan Athey
  0.00
• Beyond Conservatism: Diffusion Policies In Offline Multi-agent Reinforcement Learning (2023)
  Zhuoran Li, Ling Pan, Longbo Huang
  0.00
• The Curse Of Passive Data Collection In Batch Reinforcement Learning (2021)
  Chenjun Xiao, Ilbin Lee, Bo Dai, et al.
  0.00
• Q($\lambda$) with Off-Policy Corrections (2016)
  Anna Harutyunyan and Marc G. Bellemare and Tom Stepleton and Remi Munos
  —
• Investigating practical linear temporal difference learning (2016)
  Adam White et al.
  —
• Algorithms for Batch Hierarchical Reinforcement Learning (2016)
  Tiancheng Zhao et al.
  —
• Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning (2016)
  Philip S. Thomas and Emma Brunskill
  —
• Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics (2016)
  Michael Herman et al.
  —
• Learning Purposeful Behaviour in the Absence of Rewards (2016)
  Marlos C. Machado and Michael Bowling
  —
• Model-Free Imitation Learning with Policy Optimization (2016)
  Jonathan Ho et al.
  —
• Difference of Convex Functions Programming Applied to Control with Expert Data (2016)
  Bilal Piot et al.
  —
• Safe and Efficient Off-Policy Reinforcement Learning (2016)
  R\'emi Munos et al.
  —
• Policy Networks with Two-Stage Training for Dialogue Systems (2016)
  Mehdi Fatemi et al.
  —
• Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation (2016)
  Josiah P. Hanna et al.
  —
• Learning from Conditional Distributions via Dual Embeddings (2016)
  Bo Dai et al.
  —
• Guided Policy Search as Approximate Mirror Descent (2016)
  William Montgomery et al.
  —
• A Batch, Off-Policy, Actor-Critic Algorithm for Optimizing the Average Reward (2016)
  S.A. Murphy et al.
  —
• Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay (2016)
  Ionel-Alexandru Hosu et al.
  —
• Neuroevolution-Based Inverse Reinforcement Learning (2016)
  Karan K. Budhraja and Tim Oates
  —
• Density Matching Reward Learning (2016)
  Sungjoon Choi et al.
  —
• BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems (2016)
  Zachary C. Lipton et al.
  —
• Modelling Stock-market Investors as Reinforcement Learning Agents [Correction] (2016)
  Alvin Pastore et al.
  —
• Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning (2016)
  Yu Fan Chen et al.
  —
• Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates (2016)
  Shixiang Gu and Ethan Holly and Timothy Lillicrap and Sergey Levine
  —
• Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policies (2016)
  Daniel Hein et al.
  —
• Learning Runtime Parameters in Computer Systems with Delayed Experience Injection (2016)
  Michael Schaarschmidt et al.
  —
• Sample Efficient Actor-Critic with Experience Replay (2016)
  Ziyu Wang et al.
  —
• Combining policy gradient and Q-learning (2016)
  Brendan O'Donoghue et al.
  —