Continual Knowledge Adaptation for Reinforcement Learning

TL;DR

This paper introduces CKA-RL, a continual reinforcement learning method that effectively retains and transfers knowledge across tasks, reducing forgetting and improving performance in non-stationary environments.

Contribution

The paper proposes a novel Continual Knowledge Adaptation strategy and an Adaptive Knowledge Merging mechanism for reinforcement learning, enhancing knowledge retention and transfer across tasks.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Achieves 4.20% improvement in overall performance.

Attains 8.02% better forward transfer.

Abstract

Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing conditions. Although Continual Reinforcement Learning facilitates learning across multiple tasks, existing methods often suffer from catastrophic forgetting and inefficient knowledge utilization. To address these challenges, we propose Continual Knowledge Adaptation for Reinforcement Learning (CKA-RL), which enables the accumulation and effective utilization of historical knowledge. Specifically, we introduce a Continual Knowledge Adaptation strategy, which involves maintaining a task-specific knowledge vector pool and dynamically using historical knowledge to adapt the agent to new tasks. This process mitigates catastrophic forgetting and enables efficient knowledge transfer across tasks by preserving and adapting critical model parameters. Additionally, we propose an Adaptive Knowledge Merging mechanism that combines similar knowledge vectors to address scalability challenges, reducing memory requirements while ensuring the retention of essential knowledge. Experiments on three benchmarks demonstrate that the proposed CKA-RL outperforms state-of-the-art methods, achieving an improvement of 4.20% in overall performance and 8.02% in forward transfer. The source code is available at https://github.com/Fhujinwu/CKA-RL.