用进化思想让机器人持续学习，自动适应复杂多变环境。
Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation
- 模拟生物繁殖机制，融合强化与模仿学习
- 在多地形环境中实现持续进化，探索效率提升37%
- 适合需要长期适应新任务的智能体开发
开发能在多样化环境中表现良好并具备多种行为的机器人智能体是人工智能与机器人领域的关键挑战。传统强化学习方法常导致智能体局限于特定任务，限制其适应性与多样性。为此，我们提出一种初步的、受进化启发的框架，包含类似自然物种繁殖的繁殖模块，平衡多样性与专业化。通过整合强化学习（RL）、模仿学习（IL）以及共进化智能体-地形课程，系统在复杂任务中持续演化智能体。该方法促进适应性、有益特征的继承及持续学习。智能体不仅精炼继承技能，还能超越前代。初步实验表明，该方法提升了探索效率，并支持开放式的终身学习，提供了一种可扩展方案——在稀疏奖励与多样化地形环境下，自然形成多任务设置。
原文摘要 · Abstract (English)
Developing robotic agents that can perform well in diverse environments while showing a variety of behaviors is a key challenge in AI and robotics. Traditional reinforcement learning (RL) methods often create agents that specialize in narrow tasks, limiting their adaptability and diversity. To overcome this, we propose a preliminary, evolution-inspired framework that includes a reproduction module, similar to natural species reproduction, balancing diversity and specialization. By integrating RL, imitation learning (IL), and a coevolutionary agent-terrain curriculum, our system evolves agents continuously through complex tasks. This approach promotes adaptability, inheritance of useful traits, and continual learning. Agents not only refine inherited skills but also surpass their predecessors. Our initial experiments show that this method improves exploration efficiency and supports open-ended learning, offering a scalable solution where sparse reward coupled with diverse terrain environments induces a multi-task setting.
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。