Multi-granularity Knowledge Transfer For Continual Reinforcement Learning

Abstract

Continual reinforcement learning (CRL) empowers RL agents with the ability to learn a sequence of tasks, accumulating knowledge learned in the past and using the knowledge for problemsolving or future task learning. However, existing methods often focus on transferring fine-grained knowledge across similar tasks, which neglects the multi-granularity structure of human cognitive control, resulting in insufficient knowledge transfer across diverse tasks. To enhance coarse-grained knowledge transfer, we propose a novel framework called MT-Core (as shorthand for Multi-granularity knowledge Transfer for Continual reinforcement learning). MT-Core has a key characteristic of multi-granularity policy learning: 1) a coarsegrained policy formulation for utilizing the powerful reasoning ability of the large language model (LLM) to set goals, and 2) a fine-grained policy learning through RL which is oriented by the goals. We also construct a new policy library (knowledge base) to store policies th

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keypan2024multi

Related papers

• Continual Policy Distillation From Distributed Reinforcement Learning Teachers (2026)0.00
• Knowledge Transfer In Multi-task Deep Reinforcement Learning For Continuous Control (2020)0.00
• Task-agnostic Continual Reinforcement Learning: Gaining Insights And Overcoming Challenges (2022)0.00
• Centralized Reward Agent For Knowledge Sharing And Transfer In Multi-task Reinforcement Learning (2024)0.00
• Continual Knowledge Adaptation For Reinforcement Learning (2025)0.00
• Dynamics-adaptive Continual Reinforcement Learning Via Progressive Contextualization (2022)7.16
• Demonstration-guided Continual Reinforcement Learning In Dynamic Environments (2025)0.00
• Foundations For Transfer In Reinforcement Learning: A Taxonomy Of Knowledge Modalities (2023)0.00