| 1 |
DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting |
DODT：通过Dreamer的Actor-Critic轨迹预测增强在线决策Transformer学习 |
reinforcement learning world model dreamer |
|
|
| 2 |
DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation |
DIAR：基于扩散模型的自适应重估隐式Q学习，解决离线强化学习长程决策问题 |
reinforcement learning offline RL offline reinforcement learning |
|
|
| 3 |
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning |
提出DUSDi，用于学习解耦技能以提升分层强化学习效率 |
reinforcement learning |
|
|