用自编码器自动识别新任务和旧环境，实现无外部信号的持续强化学习。
Continual Reinforcement Learning via Autoencoder-Driven Task and New Environment Recognition
- 通过自编码器检测任务与环境变化，无需外部提示信号。
- 系统能持续学习新任务并保留旧知识，重遇旧环境时可精准调用。
- 适合需要长期适应复杂动态环境的智能体应用。
强化学习智能体的持续学习仍面临重大挑战，尤其在缺乏外部信号指示任务或环境变化的情况下，如何保存并利用已有信息。本研究探索自编码器在检测新任务及匹配已知环境方面的有效性。提出一种端到端持续学习框架，将策略优化与熟悉度自编码器相结合。该系统可在无外部信号条件下识别并学习新任务或环境，同时保留早期经验，并在再次遇到已知环境时选择性检索相关知识。初步结果表明，该方法无需外部信号即可实现持续学习，具有广阔应用前景。
原文摘要 · Abstract (English)
Continual learning for reinforcement learning agents remains a significant challenge, particularly in preserving and leveraging existing information without an external signal to indicate changes in tasks or environments. In this study, we explore the effectiveness of autoencoders in detecting new tasks and matching observed environments to previously encountered ones. Our approach integrates policy optimization with familiarity autoencoders within an end-to-end continual learning system. This system can recognize and learn new tasks or environments while preserving knowledge from earlier experiences and can selectively retrieve relevant knowledge when re-encountering a known environment. Initial results demonstrate successful continual learning without external signals to indicate task changes or reencounters, showing promise for this methodology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。