| 1 |
Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors |
提出诊断驱动的在线强化学习框架以解决离线先验的有效性问题 |
reinforcement learning world model world models |
|
|
| 2 |
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents |
提出语义一致性策略优化以解决强化学习中的信用不一致问题 |
reinforcement learning consistency policy reward shaping |
|
|
| 3 |
Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning |
提出低秩适应的内存高效策略库以解决强化学习中的存储问题 |
reinforcement learning PPO large language model |
|
|
| 4 |
Inverse Reinforcement Learning for Interpretable Keystroke Biomarkers in Parkinson's Disease |
应用逆强化学习提取帕金森病的可解释击键生物标志 |
reinforcement learning inverse reinforcement learning |
|
|
| 5 |
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources |
提出MiniOpt以解决有限资源下的优化问题 |
reinforcement learning policy learning reward design |
✅ |
|
| 6 |
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity |
提出基于自蒸馏的策略以解决输出多样性降低问题 |
reinforcement learning distillation |
|
|
| 7 |
Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization |
提出HiReLC框架以实现深度神经网络的自动化压缩 |
reinforcement learning reward shaping |
|
|
| 8 |
Knowledge Cascade: Reverse Knowledge Distillation on Nonparametric Multivariate Functional Estimation |
提出知识级联框架以解决教师模型构建瓶颈问题 |
distillation |
|
|
| 9 |
Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning |
提出低方差信任区域优化以解决多智能体强化学习中的高方差问题 |
reinforcement learning |
✅ |
|
| 10 |
Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning |
提出IF-Beta框架以提高知识蒸馏中的数据剪枝效率 |
distillation |
|
|
| 11 |
FactorLibrary: From Polynomials to Circuits via Recursive Subgoals |
提出FactorLibrary以解决有限域多项式的最小算术电路问题 |
reinforcement learning PPO SAC |
|
|
| 12 |
Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning |
提出统一框架以解决强化学习中的状态抽象问题 |
reinforcement learning |
|
|
| 13 |
Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods |
提出KNIFE方法以解决多智能体强化学习中的塑性丧失问题 |
reinforcement learning |
|
|
| 14 |
Learning with a Single Rollout via Monte Carlo Pass@k Critic |
提出单次回合的蒙特卡洛Pass@k评论者以解决语言模型的优势估计问题 |
reinforcement learning PPO |
|
|