Summary of Plancritic: Formal Planning with Human Feedback, by Owen Burns et al.
PlanCritic: Formal Planning with Human Feedback
by Owen Burns, Dana Hughes, Katia Sycara
First submitted to arxiv on: 30 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Neural and Evolutionary Computing (cs.NE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers tackle the challenge of complex planning problems in real-world domains by developing a collaborative planning system. The goal is to leverage the strengths of both humans and formal planners to achieve better results. To bridge the gap between the system’s problem representation and the real world, the authors propose modeling the problem as an online preference learning task, which allows for feedback-driven plan optimization using reinforcement learning and genetic algorithms. This approach directly optimizes the plan with respect to natural-language user preferences, bridging the gap between research in efficient planners and planning with language models. The proposed plan critic is demonstrated on a disaster recovery task, showing improved performance compared to an LLM-only neurosymbolic approach. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, scientists work together to make complex decision-making easier by combining human abilities with computer systems. They want to help humans do tasks better and faster. To do this, they use a combination of feedback from humans and computer algorithms to improve the planning process. This is important because it allows people to get more accurate results without having to spend too much time on each task. The team shows that their method works well by testing it on a specific problem related to disaster recovery. |
Keywords
» Artificial intelligence » Optimization » Reinforcement learning
