paper-with-me

홈 › Papers

Context-Aware Policy Reuse

2018-06-11 · Siyuan Li, Fangda Gu, Guangxiang Zhu, Chongjie Zhang

Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks. Existing works of policy reuse either focus on only selecting a single best source policy for transfer without considering contexts, or cannot guarantee to learn an optimal policy for a target task. To improve transfer efficiency and guarantee optimality, we develop a novel policy reuse method, called Context-Aware Policy reuSe (CAPS), that enables multi-policy transfer. Our method learns when and which source policy is best for reuse, as well as when to terminate its reuse. CAPS provides theoretical guarantees in convergence and optimality for both source policy selection and target task learning. Empirical results on a grid-based navigation domain and the Pygame Learning Environment demonstrate that CAPS significantly outperforms other state-of-the-art policy reuse methods.

📄 PDF Abstract BibTeX arXiv:1806.03793

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningTransfer Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Exploiting Contextual Structure to Generate Useful Auxiliary Tasks

2023-03-09 · Benedict Quartey, Ankit Shah, George Konidaris

Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous…

counterfactualCounterfactual Reasoningreinforcement-learningReinforcement Learning+1

AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation

2026-01-27 · Wenda Yu, Tianshi Wang, Fengling Li, Jingjing Li 외 arxiv

Vision-Language-Action (VLA) models have demonstrated strong performance in robotic manipulation, yet their closed-loop deployment is hindered by the high latency and compute cost of repeatedly running large vision-langu…

CUP: Critic-Guided Policy Reuse

2022-10-15 · Jin Zhang, Siyuan Li, Chongjie Zhang

The ability to reuse previous policies is an important aspect of human intelligence. To achieve efficient policy reuse, a Deep Reinforcement Learning (DRL) agent needs to decide when to reuse and which source policies to…

Deep Reinforcement Learning

AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse

2026-05-05 · Jie Ou, Jinyu Guo, Shiyao Guo, Yuang Li 외 arxiv

Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Language Models (LLMs). However, existing methods typically rely on a pred…

Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches

2026-05-12 · Shaoke Fang, Ziang Li, Wenfei Wu, Jiatong Ji 외 arxiv

Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt prefixes to reduce expensive prefill computation. However, its benefi…