让AI自己生成并优化任务计划，减少人工标注。
Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning
- 语言模型通过强化学习反馈自我生成和优化高阶计划。
- 在动态环境中指令遵循准确率优于基线方法，且能泛化到新指令。
- 适合需要自主规划的智能体开发，如机器人任务执行。
我们提出SuperIgor框架，用于指令跟随任务。与依赖预定义子任务的以往方法不同，SuperIgor使语言模型通过自学习机制生成并迭代优化高层计划，降低对人工数据标注的需求。该方法采用迭代联合训练：强化学习（RL）智能体学习执行生成的计划，而语言模型则根据RL反馈和偏好调整计划，形成双向改进的闭环。我们在具有丰富动态性和随机性的环境中验证该框架，结果表明，SuperIgor智能体对指令的遵循更加严格，并展现出对未见指令的强大泛化能力。
原文摘要 · Abstract (English)
We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism, reducing the need for manual dataset annotation. Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences. This creates a feedback loop where both the agent and the planner improve jointly. We validate our framework in environments with rich dynamics and stochasticity. Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions.
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。