4 results found Sort:

21
257
apache-2.0
5
[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.
Created 2023-05-22
9 commits to main branch, last one 4 months ago
[NeurIPS 2024] Official implementation for paper "Can Graph Learning Improve Planning in LLM-based Agents?"
Created 2024-05-28
55 commits to main branch, last one 3 months ago
8
45
unknown
6
Human Demo Videos to Robot Action Plans
Created 2024-10-06
47 commits to main branch, last one 4 months ago
使用langchain进行任务规划,构建子任务的会话场景资源,通过MCTS任务执行器,来让每个子任务通过在上下文中资源,通过自身反思探索来获取自身对问题的最优答案;这种方式依赖模型的对齐偏好,我们在每种偏好上设计了一个工程框架,来完成自我对不同答案的奖励进行采样策略
Created 2023-09-16
226 commits to main branch, last one 10 days ago