| 1 |
Decision Theory-Guided Deep Reinforcement Learning for Fast Learning |
提出决策理论引导的深度强化学习以解决冷启动问题 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 2 |
Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices |
提出FedLCB-Q以解决离线强化学习中的协作问题 |
reinforcement learning offline RL offline reinforcement learning |
|
|
| 3 |
Improving Token-Based World Models with Parallel Observation Prediction |
提出并行观察预测机制以提升基于令牌的世界模型性能 |
reinforcement learning world model world models |
✅ |
|
| 4 |
Differentially Private Deep Model-Based Reinforcement Learning |
提出PriMORL以解决差分隐私深度强化学习问题 |
reinforcement learning offline reinforcement learning model-based RL |
|
|
| 5 |
Dirichlet Flow Matching with Applications to DNA Sequence Design |
提出Dirichlet流匹配以解决DNA序列设计问题 |
flow matching classifier-free guidance |
✅ |
|
| 6 |
Offline Actor-Critic Reinforcement Learning Scales to Large Models |
提出离线演员-评论家强化学习以应对大规模模型挑战 |
reinforcement learning offline RL |
|
|
| 7 |
Understanding Contrastive Representation Learning from Positive Unlabeled (PU) Data |
提出正负未标记对比学习以解决有限标签问题 |
representation learning contrastive learning |
|
|
| 8 |
Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL |
提出P-MBED以解决均值场博弈中的学习复杂性问题 |
reinforcement learning model-based RL |
|
|
| 9 |
NPSVC++: Nonparallel Classifiers Encounter Representation Learning |
提出NPSVC++以解决非平行支持向量分类器的学习瓶颈问题 |
representation learning |
|
|
| 10 |
Risk-Sensitive Multi-Agent Reinforcement Learning in Network Aggregative Markov Games |
提出风险敏感的多智能体强化学习以解决网络聚合马尔可夫博弈问题 |
reinforcement learning |
|
|
| 11 |
Attention-Enhanced Prioritized Proximal Policy Optimization for Adaptive Edge Caching |
提出基于注意力机制的优先级近端策略优化以解决边缘缓存问题 |
reinforcement learning deep reinforcement learning PPO |
|
|
| 12 |
Discovering Temporally-Aware Reinforcement Learning Algorithms |
提出动态目标函数更新方法以提升强化学习算法的表现 |
reinforcement learning |
|
|
| 13 |
Stable Autonomous Flow Matching |
提出稳定自主流匹配以解决生成模型中的控制理论问题 |
flow matching |
|
|
| 14 |
FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning |
提出FedAA以解决联邦学习中的公平性与鲁棒性问题 |
reinforcement learning |
✅ |
|
| 15 |
Adaptive Activation Functions for Predictive Modeling with Sparse Experimental Data |
提出自适应激活函数以解决稀疏实验数据下的预测建模问题 |
predictive model |
|
|
| 16 |
TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning |
提出TASER以解决动态图神经网络中的噪声问题 |
representation learning |
|
|
| 17 |
Scaling Intelligent Agents in Combat Simulations for Wargaming |
提出分层强化学习框架以提升战斗模拟中的智能代理性能 |
reinforcement learning deep reinforcement learning |
|
|
| 18 |
Scaling Artificial Intelligence for Digital Wargaming in Support of Decision-Making |
提出层次强化学习框架以提升数字战争游戏中的决策支持 |
reinforcement learning deep reinforcement learning |
|
|
| 19 |
Generalized Preference Optimization: A Unified Approach to Offline Alignment |
提出广义偏好优化以统一离线对齐方法 |
RLHF DPO |
|
|
| 20 |
Learning Uncertainty-Aware Temporally-Extended Actions |
提出不确定性感知的时间扩展动作以解决动作重复问题 |
reinforcement learning policy learning |
|
|
| 21 |
Noise Contrastive Alignment of Language Models with Explicit Rewards |
提出噪声对比对齐方法以优化语言模型的奖励机制 |
DPO direct preference optimization |
|
|