English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Catastrophic forgetting poses a substantial challenge for managingintelligent agents controlled by a large model, causing performance degradationwhen these agents face new tasks. In our work, we propose a novel solution -the Progressive Prompt Decision Transformer (P2DT). This method enhances atransformer-based model by dynamically appending decision tokens during newtask training, thus fostering task-specific policies. Our approach mitigatesforgetting in continual and offline reinforcement learning scenarios. Moreover,P2DT leverages trajectories collected via traditional reinforcement learningfrom all tasks and generates new task-specific tokens during training, therebyretaining knowledge from previous studies. Preliminary results demonstrate thatour model effectively alleviates catastrophic forgetting and scales well withincreasing task environments.

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