cs.LG(2023-10-26)

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (14 🔗2) 支柱九:具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱一:机器人控制 (Robot Control) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (14 篇)

#题目一句话要点标签🔗
1 Large Language Models as Generalizable Policies for Embodied Tasks 提出LLaRP以解决视觉任务中的通用策略问题 reinforcement learning egocentric embodied AI
2 CQM: Curriculum Reinforcement Learning with a Quantized World Model 提出CQM以解决高维空间中课程强化学习的目标生成问题 reinforcement learning world model world models
3 FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing 提出FedPEAT以解决大规模模型在边缘计算中的调优问题 reinforcement learning deep reinforcement learning foundation model
4 Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning 提出期望算子以解决离线强化学习中的双模拟表示问题 reinforcement learning offline RL offline reinforcement learning
5 Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks 将DreamerV3技巧应用于PPO以提升奖励规模鲁棒性 reinforcement learning PPO dreamer
6 Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates 提出动态不变数据增强策略以提升无模型强化学习的数据效率 reinforcement learning
7 Combating Representation Learning Disparity with Geometric Harmonization 提出几何协调方法以解决长尾分布下的表示学习不均衡问题 representation learning
8 Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach 提出深度多智能体强化学习解决公平协作车辆路径规划问题 reinforcement learning
9 Coalitional Bargaining via Reinforcement Learning: An Application to Collaborative Vehicle Routing 通过强化学习提出合作博弈解决协作车辆调度问题 reinforcement learning
10 Demonstration-Regularized RL 提出演示正则化强化学习以提高样本效率 reinforcement learning behavior cloning RLHF
11 CROP: Conservative Reward for Model-based Offline Policy Optimization 提出CROP以解决离线强化学习中的过估计问题 reinforcement learning offline RL offline reinforcement learning
12 Spatio-Temporal Meta Contrastive Learning 提出CL4ST框架以解决时空图神经网络数据稀缺问题 contrastive learning
13 Learning Regularized Graphon Mean-Field Games with Unknown Graphons 提出GMFG-PPO算法以解决未知图谱的均衡学习问题 reinforcement learning PPO
14 DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic 提出DSAC-C以增强离散软演员评论家的鲁棒性 reinforcement learning SAC

🔬 支柱九:具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗
15 Toward 6G Native-AI Network: Foundation Model based Cloud-Edge-End Collaboration Framework 提出基于基础模型的6G原生AI网络框架以解决智能协作问题 foundation model
16 LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs? 提出LLM4DyG以解决动态图上的时空问题 large language model
17 PockEngine: Sparse and Efficient Fine-tuning in a Pocket 提出PockEngine以解决边缘设备上高效微调问题 large language model
18 The Expressive Power of Low-Rank Adaptation 提出低秩适应方法以提升预训练模型的微调能力 large language model
19 Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time 提出DejaVu以解决大规模语言模型推理效率问题 large language model

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
20 OptScaler: A Collaborative Framework for Robust Autoscaling in the Cloud 提出OptScaler以解决云计算中自动扩展的鲁棒性问题 MPC model predictive control

⬅️ 返回 cs.LG 首页 · 🏠 返回主页