Summary of Genplan: Generative Sequence Models As Adaptive Planners, by Akash Karthikeyan et al.
GenPlan: Generative Sequence Models as Adaptive Planners
by Akash Karthikeyan, Yash Vardhan Pant
First submitted to arxiv on: 11 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 A novel sequence model, GenPlan, is proposed to tackle challenging multi-task missions that require adapting to unseen constraints and tasks. The existing decision-making methods are limited in their ability to generalize beyond the training demonstrations, particularly when faced with temporal planning horizons or out-of-distribution tasks. GenPlan utilizes discrete-flow models for generative sequence modeling, enabling sample-efficient exploration and exploitation. This framework relies on an iterative denoising procedure to generate a sequence of goals and actions, capturing multi-modal action distributions and facilitating goal and task discovery. Experimental results demonstrate the effectiveness of GenPlan, outperforming state-of-the-art methods by over 10% in adaptive planning tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to help robots plan is developed called GenPlan. Right now, robots have trouble when they need to do multiple things at once and find new goals or open doors they’ve never seen before. This makes it hard for them to adapt to new situations. To fix this, GenPlan uses a special kind of model that can generate sequences of actions and goals. It’s like a puzzle solver! The robot can use past experiences to figure out what to do in new situations. GenPlan is better than other methods at planning because it can learn from its mistakes and try different things until it gets the right answer. |
Keywords
» Artificial intelligence » Multi modal » Multi task » Sequence model
