Demonstration-guided Continual Reinforcement Learning In Dynamic Environments

Abstract

Reinforcement learning (RL) excels in various applications but struggles in dynamic environments where the underlying Markov decision process evolves. Continual reinforcement learning (CRL) enables RL agents to continually learn and adapt to new tasks, but balancing stability (preserving prior knowledge) and plasticity (acquiring new knowledge) remains challenging. Existing methods primarily address the stability-plasticity dilemma through mechanisms where past knowledge influences optimization but rarely affects the agent's behavior directly, which may hinder effective knowledge reuse and efficient learning. In contrast, we propose demonstration-guided continual reinforcement learning (DGCRL), which stores prior knowledge in an external, self-evolving demonstration repository that directly guides RL exploration and adaptation. For each task, the agent dynamically selects the most relevant demonstration and follows a curriculum-based strategy to accelerate learning, gradually shifting

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2025demonstration

Related papers

• Dynamics-adaptive Continual Reinforcement Learning Via Progressive Contextualization (2022)7.16
• A Survey Of Continual Reinforcement Learning (2025)0.00
• Advancements And Challenges In Continual Reinforcement Learning: A Comprehensive Review (2025)0.00
• Continual Policy Distillation From Distributed Reinforcement Learning Teachers (2026)0.00
• Interactive Reinforcement Learning With Dynamic Reuse Of Prior Knowledge From Human/agent's Demonstration (2018)8.60
• Continual Knowledge Adaptation For Reinforcement Learning (2025)0.00
• Continual Reinforcement Learning By Planning With Online World Models (2025)0.00
• Safe Continual Reinforcement Learning In Non-stationary Environments (2026)12.89