English
Related papers

Related papers: Cold-RL: Learning Cache Eviction with Offline Rein…

200 papers

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Machine Learning · Computer Science 2025-10-07 Lianghuan Huang , Sagnik Anupam , Insup Lee , Shuo Li , Osbert Bastani

In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching systems improve hit rates mainly through…

A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL. However, existing works heavily rely on the purity of the data,…

Machine Learning · Computer Science 2022-10-20 Chengqian Gao , Ke Xu , Liu Liu , Deheng Ye , Peilin Zhao , Zhiqiang Xu

We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an…

Machine Learning · Computer Science 2026-05-12 Qiyang Li , Zhiyuan Zhou , Sergey Levine

The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on…

Computation and Language · Computer Science 2026-02-12 Luca Moschella , Laura Manduchi , Ozan Sener

Reinforcement learning (RL) has achieved strong results, but deploying visual policies on resource-constrained edge devices remains challenging due to computational cost and communication latency. Many deployments therefore offload policy…

Machine Learning · Computer Science 2025-12-24 Carlos Purves

Prompt caching is critical for reducing latency and cost in LLM inference: OpenAI and Anthropic report up to 50-90% cost savings through prompt reuse. Despite its widespread success, little is known about what constitutes an optimal prompt…

Systems and Control · Electrical Eng. & Systems 2025-10-20 Wenxin Zhang , Yueying Li , Ciamac C. Moallemi , Tianyi Peng

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data…

Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human…

Machine Learning · Computer Science 2023-06-01 Philip J. Ball , Laura Smith , Ilya Kostrikov , Sergey Levine

A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave…

Machine Learning · Computer Science 2024-01-23 Mitsuhiko Nakamoto , Yuexiang Zhai , Anikait Singh , Max Sobol Mark , Yi Ma , Chelsea Finn , Aviral Kumar , Sergey Levine

Scaling the input context length of a large language model (LLM) incurs a significant increase in computation cost and memory footprint to maintain the attention key-value (KV) cache. Existing KV cache compression methods suffer from…

Computation and Language · Computer Science 2025-01-31 Yuxiang Huang , Binhang Yuan , Xu Han , Chaojun Xiao , Zhiyuan Liu

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Machine Learning · Computer Science 2025-10-06 Aleksei Arzhantsev , Otmane Sakhi , Flavian Vasile

KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…

Machine Learning · Computer Science 2026-01-28 Fangzhou Wu , Sandeep Silwal , Qiuyi , Zhang

Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due to the iterative…

Machine Learning · Computer Science 2025-05-30 Nicolas Espinosa-Dice , Yiyi Zhang , Yiding Chen , Bradley Guo , Owen Oertell , Gokul Swamy , Kiante Brantley , Wen Sun

Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or costs of online experimentation. This work investigates the…

Systems and Control · Electrical Eng. & Systems 2025-07-31 Alex Durkin , Jasper Stolte , Matthew Jones , Raghuraman Pitchumani , Bei Li , Christian Michler , Mehmet Mercangöz

Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios where exploration can be expensive or unsafe. Previous works…

Machine Learning · Computer Science 2022-12-05 Yiqin Yang , Hao Hu , Wenzhe Li , Siyuan Li , Jun Yang , Qianchuan Zhao , Chongjie Zhang

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

Machine Learning · Computer Science 2023-09-06 Qisen Yang , Shenzhi Wang , Qihang Zhang , Gao Huang , Shiji Song

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected and labeled datasets, which eliminates the time-consuming data collection in online RL. However, offline RL still bears a large burden of…

Machine Learning · Computer Science 2023-10-17 Jinxin Liu , Lipeng Zu , Li He , Donglin Wang

Offline reinforcement learning (RL) enables policy learning from fixed datasets without further environment interaction, making it particularly valuable in high-risk or costly domains. Extreme $Q$-Learning (XQL) is a recent offline RL…

Machine Learning · Computer Science 2026-04-15 Xinming Gao , Shangzhe Li , Yujin Cai , Wenwu Yu
‹ Prev 1 2 3 10 Next ›