P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer

Zhiyuan Wang,Xiaoyang Qu, Jing Xiao,Bokui Chen,Jianzong Wang

CoRR(2024)

引用 0|浏览23
暂无评分
摘要
Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive Prompt Decision Transformer (P2DT). This method enhances a transformer-based model by dynamically appending decision tokens during new task training, thus fostering task-specific policies. Our approach mitigates forgetting in continual and offline reinforcement learning scenarios. Moreover, P2DT leverages trajectories collected via traditional reinforcement learning from all tasks and generates new task-specific tokens during training, thereby retaining knowledge from previous studies. Preliminary results demonstrate that our model effectively alleviates catastrophic forgetting and scales well with increasing task environments.
更多
查看译文
关键词
Continual Learning,Offline Reinforcement Learning,Prompt Learning,AI Agent
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要