扩散式任务无关里程碑规划器
Diffused Task-Agnostic Milestone Planner
AI总结：
提出扩散式任务无关里程碑规划器，在潜在空间生成里程碑并由智能体跟踪，以支持长期规划、视觉控制和多任务决策，并在离线RL与视觉操控基准上取得领先性能。
摘要：
近年来，利用序列建模预测未来轨迹来解决决策问题已展现出良好效果。本文进一步将序列预测方法用于长期规划、基于视觉的控制和多任务决策等更广泛领域。为此，我们提出一种方法，利用基于扩散的生成式序列模型在潜在空间中规划一系列里程碑，并让智能体遵循这些里程碑完成给定任务。所提方法能够学习与控制相关的低维里程碑潜在表示，从而使高效执行长期规划和基于视觉的控制成为可能。此外，本方法利用扩散模型的生成灵活性，可为多任务决策规划多样化轨迹。我们在离线强化学习（RL）基准和一个视觉操控环境中验证了所提方法。结果表明，本方法在解决长时域、稀疏奖励任务和多任务问题方面优于离线RL方法，同时在最具挑战性的基于视觉的操控基准上达到最先进性能。
英文摘要：
Addressing decision-making problems using sequence modeling to predict future trajectories shows promising results in recent years. In this paper, we take a step further to leverage the sequence predictive method in wider areas such as long-term planning, vision-based control, and multi-task decision-making. To this end, we propose a method to utilize a diffusion-based generative sequence model to plan a series of milestones in a latent space and to have an agent to follow the milestones to accomplish a given task. The proposed method can learn control-relevant, low-dimensional latent representations of milestones, which makes it possible to efficiently perform long-term planning and vision-based control. Furthermore, our approach exploits generation flexibility of the diffusion model, which makes it possible to plan diverse trajectories for multi-task decision-making. We demonstrate the proposed method across offline reinforcement learning (RL) benchmarks and an visual manipulation environment. The results show that our approach outperforms offline RL methods in solving long-horizon, sparse-reward tasks and multi-task problems, while also achieving the state-of-the-art performance on the most challenging vision-based manipulation benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
