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.
@article{arxiv.2401.11666,
title = {P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer},
author = {Zhiyuan Wang and Xiaoyang Qu and Jing Xiao and Bokui Chen and Jianzong Wang},
journal= {arXiv preprint arXiv:2401.11666},
year = {2025}
}
Comments
Accepted by the 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)