全部 |
  • 全部
  • 题名
  • 作者
  • 机构
  • 关键词
  • NSTL主题词
  • 摘要
检索 二次检索 AI检索
外文文献 中文文献
筛选条件:

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. 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

7. 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

8. 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

9. 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
关键词: Deep reinforcement learning |  Inverse reinforcement learning |  Preference based reinforcement learning |  Remote operated vehicles

10. Altruism in Fuzzy Reinforcement Learning NSTL国家科技图书文献中心

Rachel M. Haighton |  Howard M. Schwartz... -  《IEEE transactions on computational social systems》 - 2025,12(1) - 348~361 - 共14页

摘要: hyperparameters in multiagent reinforcement learning (MARL |  using fuzzy actor critic learning algorithms in either |  of noise applied to actor during learning. The | We propose using a genetic algorithm to select | ) settings. In particular, we look at this in the context
关键词: Reinforcement learning |  Games |  Genetic algorithms |  Optimization |  Noise |  Fuzzy logic |  Visualization |  Training |  Standards |  Robots
检索条件Reinforcement learning
  • 检索词扩展

NSTL主题词

  • NSTL学科导航