Summary of Learning in Hybrid Active Inference Models, by Poppy Collis et al.
Learning in Hybrid Active Inference Models
by Poppy Collis, Ryan Singh, Paul F Kinghorn, Christopher L Buckley
First submitted to arxiv on: 2 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Systems and Control (eess.SY)
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 hierarchical hybrid active inference agent is introduced, which combines a high-level discrete active inference planner with a low-level continuous active inference controller. The agent uses recent work in recurrent switching linear dynamical systems (rSLDS) to learn meaningful discrete representations from complex continuous dynamics. This allows for temporally-abstracted sub-goals, exploration bonuses, and caching of approximate solutions to low-level problems. Applications include the sparse Continuous Mountain Car task, demonstrating fast system identification and successful planning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new AI model is created that helps computers make decisions by combining two types of thinking: one that works with lots of detail (continuous) and another that works with simple ideas (discrete). This allows the computer to learn and adapt in a more flexible way. The model uses an existing idea called active inference, but adds some new features like being able to focus on specific goals and using information about what’s possible to make better decisions. |
Keywords
» Artificial intelligence » Inference
