NSTL国家科技图书文献中心

1. Reinforcement Learning Meets Visual Odometry NSTL国家科技图书文献中心

Nico Messikommer | Giovanni Cioffi ... - 《Computer Vision - ECCV 2024,Part LIX》 - European Conference on Computer Vision - 2025, - 76～92 - 共17页

摘要： decision-making task and applying Reinforcement Learning | Visual Odometry (VO) is essential to | downstream mobile robotics and augmented/virtual reality | tasks. Despite recent advances, existing VO methods | still rely on heuristic design choices that require

关键词： Visual odometry | Reinforcement learning

2. Contextual Transformers for Goal-Oriented Reinforcement Learning NSTL国家科技图书文献中心

Oliver Dippel | Alexei Lisitsa ... - 《Artificial Intelligence XLI,Part I》 - SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence - 2025, - 207～220 - 共14页

摘要： been utilized for reinforcement* learning (RL) by* | across deep-learning* disciplines due to their* | learning in-context. In in-context learning for decision | the in-context learning* abilities of transformer* | task inference during evaluation. By learning* to*

关键词： Goal-Oriented reinforcement learning | In-Context reinforcement learning | Transformer-Based reinforcement learning

3. Using Federated Learning Techniques to Generalize Reinforcement Learning Approaches NSTL国家科技图书文献中心

Alberto Tellaeche Ig... | Ignacio Fidalgo Asto...... - 《Hybrid Artificial Intelligent Systems,Part II》 - International Conference on Hybrid Artificial Intelligence Systems - 2025, - 292～303 - 共12页

摘要： reinforcement learning algorithms compensating for their less | efficient aspects. To this end, reinforcement learning | reinforcement learning approaches. | research work explores federated learning* techniques to* | generate more robust and efficient learning* models*

关键词： Reinforcement learning | Federated learning | Optimization

4. Emergent Dominance Hierarchies in Reinforcement Learning Agents NSTL国家科技图书文献中心

Ram Rachum | Yonatan Nakar ... - 《Coordination,Organizations,Institutions,Norms,and Ethics for Governance of Multi-Agent Systems XVII》 - International Conference on Autonomous Agents and Multi-Agent Systems | International Workshop on Coordination,Organizations,Institutions,Norms,and Ethics for Governance of Multi-Agent Systems - 2025, - 41～56 - 共16页

摘要：Modern Reinforcement* Learning (RL) algorithms* | tasks. Multi-agent reinforcement* learning (MARL* | are able to outperform humans in a wide variety of | ) settings present additional challenges, and successful | cooperation in mixed-motive groups of agents depends on a

关键词： Multi-Agent reinforcement learning | Reinforcement learning | Cultural evolution | Multi-Agent systems | Cooperative AI

5. Large-Scale Reinforcement Learning for Diffusion Models NSTL国家科技图书文献中心

Yinan Zhang | Eric Tzeng ... - 《Computer Vision - ECCV 2024,Part LXIII》 - European Conference on Computer Vision - 2025, - 1～17 - 共17页

摘要： models using Reinforcement* Learning (RL) with a diverse* | Text-to-image diffusion models are cutting | -edge deep generative models that have demonstrated | impressive capabilities in generating high-quality images | . However, these models are susceptible to implicit biases

关键词： Diffusion model | Reinforcement learning

6. RLPortfolio: Reinforcement Learning for Financial Portfolio Optimization NSTL国家科技图书文献中心

Caio de Souza Barbos... | Anna Helena Reali Co... - 《Intelligent Systems,Part III》 - Brazilian Conference on Intelligent Systems - 2025, - 412～426 - 共15页

摘要： reinforcement learning agent that learns an optimal investment | , train and evaluate reinforcement* learning agents whose* | Portfolio optimization is a task in which an | agent constantly rebalances a predefined portfolio of | assets in order to mitigate losses and maximize profits

关键词： Reinforcement learning | Portfolio optimization | Quantitative finance

7. AutoMiner: Reinforcement Learning-Based Mining Attack Simulator NSTL国家科技图书文献中心

Wei Li | Lide Xue ... - 《Algorithms and Architectures for Parallel Processing,Part I》 - International Conference on Algorithms and Architectures for Parallel Processing - 2025, - 222～241 - 共20页

摘要： reinforcement learning-based framework that integrates Miner | As blockchain technology rapidly advances, it | faces significant security threats from attacks like | selfish mining, which exploit consensus algorithm | vulnerabilities, undermining system security. Traditional

关键词： Blockchain | Reinforcement learning | Security analysis

8. Laser simulation and reinforcement learning mode locking NSTL国家科技图书文献中心

Junhao Xue | Tianyue Wang ... - 《International Conference on Optical and Photonic Engineering (icOPEN 2024)》 - International Conference on Optical and Photonic Engineering - 2025, - 135091Z.1～135091Z.6 - 共6页

摘要： Reinforcement Learning (RL) to train the mode-locking | introduced a reinforcement* learning algorithm to achieve an* | show that the reinforcement* learning algorithm has* | simulation and reinforcement* learning can effectively* | In this paper, the generation of ultrafast

关键词： Fiber laser | Simulation | Reinforcement learning | Laser mode-locking

9. Escape Routing Using Deep Reinforcement Learning NSTL国家科技图书文献中心

Hsu Fu Cheng | Dun Wei Cheng - 《International Workshop on Advanced Imaging Technology (IWAIT) 2025》 - International Workshop on Advanced Imaging Technology - 2025, - 135101B.1～135101B.5 - 共5页

摘要： a Deep Reinforcement* Learning (DRL)-based solution* | of Deep Reinforcement* Learning in solving escape* | Escape routing is a critical task in the | design of printed circuit boards (PCB) and integrated | circuits (IC), aiming to establish effective connections

关键词： Escape routing | Deep reinforcement learning | Printed circuit boards

10. Deep reinforcement learning from human preferences for ROV path tracking NSTL国家科技图书文献中心

Niu S. | Pan X.... - 《Ocean engineering》 - 2025,317(Feb.1) - 1.1～1.12 - 共12页

摘要： flexibility. Deep reinforcement* learning has been used to* | implement a Preference-based Reinforcement* Learning (PbRL* | reinforcement learning PPO algorithm from predefined reward | method learning* from human preferences over traditional* | function and GAIL algorithm learning* from demonstrated*

摘要： decision-making task and applying Reinforcement Learning | Visual Odometry (VO) is essential to | downstream mobile robotics and augmented/virtual reality | tasks. Despite recent advances, existing VO methods | still rely on heuristic design choices that require

关键词： Visual odometry | Reinforcement learning

摘要： been utilized for reinforcement* learning (RL) by* | across deep-learning* disciplines due to their* | learning in-context. In in-context learning for decision | the in-context learning* abilities of transformer* | task inference during evaluation. By learning* to*

关键词： Goal-Oriented reinforcement learning | In-Context reinforcement learning | Transformer-Based reinforcement learning

摘要： reinforcement learning algorithms compensating for their less | efficient aspects. To this end, reinforcement learning | reinforcement learning approaches. | research work explores federated learning* techniques to* | generate more robust and efficient learning* models*

关键词： Reinforcement learning | Federated learning | Optimization

摘要：Modern Reinforcement* Learning (RL) algorithms* | tasks. Multi-agent reinforcement* learning (MARL* | are able to outperform humans in a wide variety of | ) settings present additional challenges, and successful | cooperation in mixed-motive groups of agents depends on a

关键词： Multi-Agent reinforcement learning | Reinforcement learning | Cultural evolution | Multi-Agent systems | Cooperative AI

摘要： models using Reinforcement* Learning (RL) with a diverse* | Text-to-image diffusion models are cutting | -edge deep generative models that have demonstrated | impressive capabilities in generating high-quality images | . However, these models are susceptible to implicit biases

关键词： Diffusion model | Reinforcement learning

摘要： reinforcement learning agent that learns an optimal investment | , train and evaluate reinforcement* learning agents whose* | Portfolio optimization is a task in which an | agent constantly rebalances a predefined portfolio of | assets in order to mitigate losses and maximize profits

关键词： Reinforcement learning | Portfolio optimization | Quantitative finance

摘要： reinforcement learning-based framework that integrates Miner | As blockchain technology rapidly advances, it | faces significant security threats from attacks like | selfish mining, which exploit consensus algorithm | vulnerabilities, undermining system security. Traditional

关键词： Blockchain | Reinforcement learning | Security analysis

摘要： Reinforcement Learning (RL) to train the mode-locking | introduced a reinforcement* learning algorithm to achieve an* | show that the reinforcement* learning algorithm has* | simulation and reinforcement* learning can effectively* | In this paper, the generation of ultrafast

关键词： Fiber laser | Simulation | Reinforcement learning | Laser mode-locking

摘要： a Deep Reinforcement* Learning (DRL)-based solution* | of Deep Reinforcement* Learning in solving escape* | Escape routing is a critical task in the | design of printed circuit boards (PCB) and integrated | circuits (IC), aiming to establish effective connections

关键词： Escape routing | Deep reinforcement learning | Printed circuit boards

关键词： Deep reinforcement learning | Inverse reinforcement learning | Preference based reinforcement learning | Remote operated vehicles

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： decision-making task and applying Reinforcement Learning | Visual Odometry (VO) is essential to | downstream mobile robotics and augmented/virtual reality | tasks. Despite recent advances, existing VO methods | still rely on heuristic design choices that require

关键词： Visual odometry | Reinforcement learning

摘要： been utilized for reinforcement learning (RL) by | across deep-learning disciplines due to their | learning in-context. In in-context learning for decision | the in-context learning abilities of transformer | task inference during evaluation. By learning to

关键词： Goal-Oriented reinforcement learning | In-Context reinforcement learning | Transformer-Based reinforcement learning

摘要： reinforcement learning algorithms compensating for their less | efficient aspects. To this end, reinforcement learning | reinforcement learning approaches. | research work explores federated learning techniques to | generate more robust and efficient learning models

关键词： Reinforcement learning | Federated learning | Optimization

摘要：Modern Reinforcement Learning (RL) algorithms | tasks. Multi-agent reinforcement learning (MARL | are able to outperform humans in a wide variety of | ) settings present additional challenges, and successful | cooperation in mixed-motive groups of agents depends on a

关键词： Multi-Agent reinforcement learning | Reinforcement learning | Cultural evolution | Multi-Agent systems | Cooperative AI

摘要： models using Reinforcement Learning (RL) with a diverse | Text-to-image diffusion models are cutting | -edge deep generative models that have demonstrated | impressive capabilities in generating high-quality images | . However, these models are susceptible to implicit biases

关键词： Diffusion model | Reinforcement learning

摘要： reinforcement learning agent that learns an optimal investment | , train and evaluate reinforcement learning agents whose | Portfolio optimization is a task in which an | agent constantly rebalances a predefined portfolio of | assets in order to mitigate losses and maximize profits

关键词： Reinforcement learning | Portfolio optimization | Quantitative finance

摘要： reinforcement learning-based framework that integrates Miner | As blockchain technology rapidly advances, it | faces significant security threats from attacks like | selfish mining, which exploit consensus algorithm | vulnerabilities, undermining system security. Traditional

关键词： Blockchain | Reinforcement learning | Security analysis

摘要： Reinforcement Learning (RL) to train the mode-locking | introduced a reinforcement learning algorithm to achieve an | show that the reinforcement learning algorithm has | simulation and reinforcement learning can effectively | In this paper, the generation of ultrafast

关键词： Fiber laser | Simulation | Reinforcement learning | Laser mode-locking

摘要： a Deep Reinforcement Learning (DRL)-based solution | of Deep Reinforcement Learning in solving escape | Escape routing is a critical task in the | design of printed circuit boards (PCB) and integrated | circuits (IC), aiming to establish effective connections

关键词： Escape routing | Deep reinforcement learning | Printed circuit boards

关键词： Deep reinforcement learning | Inverse reinforcement learning | Preference based reinforcement learning | Remote operated vehicles

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： been utilized for reinforcement* learning (RL) by* | across deep-learning* disciplines due to their* | learning in-context. In in-context learning for decision | the in-context learning* abilities of transformer* | task inference during evaluation. By learning* to*

摘要： reinforcement learning algorithms compensating for their less | efficient aspects. To this end, reinforcement learning | reinforcement learning approaches. | research work explores federated learning* techniques to* | generate more robust and efficient learning* models*

摘要：Modern Reinforcement* Learning (RL) algorithms* | tasks. Multi-agent reinforcement* learning (MARL* | are able to outperform humans in a wide variety of | ) settings present additional challenges, and successful | cooperation in mixed-motive groups of agents depends on a

摘要： models using Reinforcement* Learning (RL) with a diverse* | Text-to-image diffusion models are cutting | -edge deep generative models that have demonstrated | impressive capabilities in generating high-quality images | . However, these models are susceptible to implicit biases

摘要： reinforcement learning agent that learns an optimal investment | , train and evaluate reinforcement* learning agents whose* | Portfolio optimization is a task in which an | agent constantly rebalances a predefined portfolio of | assets in order to mitigate losses and maximize profits

摘要： Reinforcement Learning (RL) to train the mode-locking | introduced a reinforcement* learning algorithm to achieve an* | show that the reinforcement* learning algorithm has* | simulation and reinforcement* learning can effectively* | In this paper, the generation of ultrafast

摘要： a Deep Reinforcement* Learning (DRL)-based solution* | of Deep Reinforcement* Learning in solving escape* | Escape routing is a critical task in the | design of printed circuit boards (PCB) and integrated | circuits (IC), aiming to establish effective connections