cs.LG(2025-03-24)
📊 共 7 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱二:RL算法与架构 (RL & Architecture) (4)
支柱一:机器人控制 (Robot Control) (2 🔗1)
支柱九:具身大模型 (Embodied Foundation Models) (1)
🔬 支柱二:RL算法与架构 (RL & Architecture) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild | SimpleRL-Zoo:探索和驯服零强化学习,用于通用开放基础模型 | reinforcement learning instruction following chain-of-thought | ||
| 2 | Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer Learning | 提出基于超网络的持续强化学习框架,用于暖通空调系统控制,提升样本效率和泛化能力。 | reinforcement learning deep reinforcement learning DRL | ||
| 3 | Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures | 提出Distil-xLSTM,通过知识蒸馏提升xLSTM在NLP任务中的效率。 | Mamba large language model | ||
| 4 | Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners | 提出基于偏好隐空间嵌入的扩散规划器,高效对齐人类偏好 | reinforcement learning RLHF |
🔬 支柱一:机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Bootstrapped Model Predictive Control | 提出Bootstrapped MPC,通过自举学习策略提升连续控制任务性能。 | locomotion MPC model predictive control | ✅ | |
| 6 | Evolutionary Policy Optimization | 提出进化策略优化(EPO),结合进化算法与策略梯度提升强化学习性能。 | legged locomotion locomotion manipulation |
🔬 支柱九:具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Solving Situation Puzzles with Large Language Model and External Reformulation | 提出外部重构方法,提升大语言模型在情境谜题中的推理能力 | large language model |