English
Related papers

Related papers: Extreme Region Policy Distillation

200 papers

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

Machine Learning · Computer Science 2025-10-06 Yuda Song , Dhruv Rohatgi , Aarti Singh , J. Andrew Bagnell

Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hinges on a few local decisions. Existing online policy distillation (OPD) provides denser…

Artificial Intelligence · Computer Science 2026-05-27 Yanfei Zhang , Xu Lin , Chenglin Wu

Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of…

Computation and Language · Computer Science 2026-04-23 Wenhong Zhu , Ruobing Xie , Rui Wang , Pengfei Liu

Reinforcement learning (RL) has become a central component of post-training for large language models (LLMs), particularly for complex reasoning tasks that require stable optimization over long generation horizons. However, achieving…

Machine Learning · Computer Science 2026-02-17 Yuepeng Sheng , Yuwei Huang , Shuman Liu , Anxiang Zeng , Haibo Zhang

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

Machine Learning · Computer Science 2026-04-13 Zhaoyang Zhang , Shuli Jiang , Yantao Shen , Yuting Zhang , Dhananjay Ram , Shuo Yang , Zhuowen Tu , Wei Xia , Stefano Soatto

Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques. On the other hand, on-policy algorithms are often more stable and easier to…

Machine Learning · Computer Science 2017-06-02 Shixiang Gu , Timothy Lillicrap , Zoubin Ghahramani , Richard E. Turner , Bernhard Schölkopf , Sergey Levine

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…

Machine Learning · Computer Science 2021-11-02 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Decision transformer based sequential policies have emerged as a powerful paradigm in offline reinforcement learning (RL), yet their efficacy remains constrained by the quality of static datasets and inherent architectural limitations.…

Machine Learning · Computer Science 2026-03-05 Yihao Qin , Yuanfei Wang , Hang Zhou , Peiran Liu , Hao Dong , Yiding Ji

Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised…

Machine Learning · Computer Science 2026-05-27 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor W. Tsang , Yang You

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

Robotics · Computer Science 2023-10-16 Jinning Li , Xinyi Liu , Banghua Zhu , Jiantao Jiao , Masayoshi Tomizuka , Chen Tang , Wei Zhan

Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the…

Computation and Language · Computer Science 2026-01-30 Jing Xiong , Hui Shen , Shansan Gong , Yuxin Cheng , Jianghan Shen , Chaofan Tao , Haochen Tan , Haoli Bai , Lifeng Shang , Ngai Wong

Balancing exploration and exploitation remains a central challenge in reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs). Current RLVR methods often overemphasize exploitation, leading to entropy…

Computation and Language · Computer Science 2026-04-14 Liang Chen , Xueting Han , Qizhou Wang , Bo Han , Jing Bai , Hinrich Schutze , Kam-Fai Wong

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning…

Machine Learning · Computer Science 2026-03-26 Ken Ding

Aligning large language models (LLMs) on domain-specific data remains a fundamental challenge. Supervised fine-tuning (SFT) offers a straightforward way to inject domain knowledge but often degrades the model's generality. In contrast,…

Machine Learning · Computer Science 2026-02-12 Linxuan Xia , Xiaolong Yang , Yongyuan Chen , Enyue Zhao , Deng Cai , Yasheng Wang , Boxi Wu

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, long-horizon settings. However, transferring capabilities…

Machine Learning · Computer Science 2026-02-17 Emiliano Penaloza , Dheeraj Vattikonda , Nicolas Gontier , Alexandre Lacoste , Laurent Charlin , Massimo Caccia

Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally deviates from the ideal on-policy objective. To address this…

Machine Learning · Computer Science 2026-05-19 Xianwei Chen , Shimin Zhang , Jibin Wu

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network…

Deep reinforcement learning with domain randomization learns a control policy in various simulations with randomized physical and sensor model parameters to become transferable to the real world in a zero-shot setting. However, a huge…

Robotics · Computer Science 2023-04-11 Yuki Kadokawa , Lingwei Zhu , Yoshihisa Tsurumine , Takamitsu Matsubara

On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We…

Machine Learning · Computer Science 2026-05-27 Yuanyi Wang , Su Lu , Yanggan Gu , Pengkai Wang , Yifan Yang , Zhaoyi Yan , Congkai Xie , Jianmin Wu , Hongxia Yang

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly…

Machine Learning · Computer Science 2026-04-03 Gengsheng Li , Tianyu Yang , Junfeng Fang , Mingyang Song , Mao Zheng , Haiyun Guo , Dan Zhang , Jinqiao Wang , Tat-Seng Chua