| 1 |
Vision-Language Models Provide Promptable Representations for Reinforcement Learning |
提出利用视觉语言模型提升强化学习表现的方法 |
reinforcement learning instruction following chain-of-thought |
|
|
| 2 |
Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning |
提出扩散世界模型以解决离线强化学习中的未来状态预测问题 |
reinforcement learning offline reinforcement learning world model |
|
|
| 3 |
DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design |
提出数据正则化环境设计以解决强化学习的零-shot迁移问题 |
reinforcement learning deep reinforcement learning zero-shot transfer |
✅ |
|
| 4 |
Contrastive Diffuser: Planning Towards High Return States via Contrastive Learning |
提出对比扩散器以解决离线强化学习中的低回报轨迹问题 |
reinforcement learning policy learning offline RL |
|
|
| 5 |
Frugal Actor-Critic: Sample Efficient Off-Policy Deep Reinforcement Learning Using Unique Experiences |
提出节约型演员-评论家方法以提高样本效率 |
reinforcement learning deep reinforcement learning |
|
|
| 6 |
Deep Reinforcement Learning for Picker Routing Problem in Warehousing |
提出基于深度强化学习的拣货员路径优化方法 |
reinforcement learning deep reinforcement learning |
|
|
| 7 |
Is Mamba Capable of In-Context Learning? |
提出Mamba模型以解决长输入序列的上下文学习问题 |
Mamba state space model foundation model |
|
|
| 8 |
Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning |
提出单一自回归模型以优化离线强化学习策略 |
reinforcement learning offline reinforcement learning |
|
|
| 9 |
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem |
提出遗忘缓解方法以优化强化学习模型微调 |
reinforcement learning foundation model |
|
|
| 10 |
A Survey on Transformer Compression |
综述Transformer压缩方法以降低模型成本 |
Mamba distillation large language model |
|
|
| 11 |
A Theoretical Framework for Partially Observed Reward-States in RLHF |
提出部分观察奖励状态的框架以改进人类反馈强化学习 |
reinforcement learning RLHF |
|
|
| 12 |
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning |
提出基于效用的强化学习以统一单目标与多目标学习 |
reinforcement learning policy learning |
|
|
| 13 |
Assessing the Impact of Distribution Shift on Reinforcement Learning Performance |
提出评估方法以应对强化学习中的分布转移问题 |
reinforcement learning |
|
|
| 14 |
Single- vs. Dual-Policy Reinforcement Learning for Dynamic Bike Rebalancing |
提出单政策与双政策强化学习以解决动态自行车再平衡问题 |
reinforcement learning |
|
|
| 15 |
Minimum Description Length and Generalization Guarantees for Representation Learning |
提出基于最小描述长度的表示学习泛化保证方法 |
representation learning |
|
|
| 16 |
Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applications |
提出显式流匹配方法以提升流生成模型训练效率 |
flow matching |
|
|
| 17 |
A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning |
提出多步损失函数以解决模型基强化学习中的动态学习问题 |
reinforcement learning |
|
|
| 18 |
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays |
提出辅助延迟强化学习以解决延迟反馈问题 |
reinforcement learning |
✅ |
|
| 19 |
Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning |
提出Open RL Benchmark以解决强化学习实验复现难题 |
reinforcement learning |
|
|
| 20 |
Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence |
提出理论框架以解决视觉强化学习中的泛化差距问题 |
reinforcement learning |
|
|
| 21 |
Decoding-time Realignment of Language Models |
提出解码时重对齐方法以优化语言模型对人类偏好的适应性 |
reinforcement learning RLHF |
|
|
| 22 |
Verifiable evaluations of machine learning models using zkSNARKs |
提出可验证的机器学习模型评估方法以解决透明性问题 |
world model world models |
|
|