| 1 |
Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine |
提出LARL-RM以自动化强化学习中的奖励机器问题 |
reinforcement learning large language model chain-of-thought |
|
|
| 2 |
Self-Correcting Self-Consuming Loops for Generative Model Training |
提出自我修正自我消耗循环以稳定生成模型训练 |
representation learning motion synthesis human motion |
|
|
| 3 |
Towards Generalized Inverse Reinforcement Learning |
提出广义逆强化学习以解决MDP组件学习问题 |
reinforcement learning inverse reinforcement learning |
|
|
| 4 |
Rethinking Graph Masked Autoencoders through Alignment and Uniformity |
提出AUG-MAE以解决GraphMAE在对齐与均匀性上的不足 |
masked autoencoder MAE contrastive learning |
|
|
| 5 |
ODIN: Disentangled Reward Mitigates Hacking in RLHF |
提出ODIN以解决RLHF中的奖励黑客问题 |
reinforcement learning RLHF |
|
|
| 6 |
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model |
提出一种基于一般偏好模型的在线迭代强化学习方法 |
reinforcement learning RLHF |
|
|
| 7 |
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning |
提出分布式强化学习以获得二阶界限解决RL问题 |
reinforcement learning offline RL |
|
|
| 8 |
Training Heterogeneous Client Models using Knowledge Distillation in Serverless Federated Learning |
提出知识蒸馏方法以解决异构客户端模型的联邦学习问题 |
distillation |
|
|
| 9 |
Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning |
提出迭代帕累托参考优化以解决多目标强化学习中的帕累托前沿问题 |
reinforcement learning |
|
|
| 10 |
Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning |
提出CEQR-DQN以解决强化学习中的不确定性问题 |
reinforcement learning |
|
|
| 11 |
An Empirical Study on the Power of Future Prediction in Partially Observable Environments |
提出自预测辅助任务以提升部分可观测环境中的强化学习表现 |
reinforcement learning DRL representation learning |
|
|