Summary of Spatial-aware Decision-making with Ring Attractors in Reinforcement Learning Systems, by Marcos Negre Saura et al.
Spatial-aware decision-making with ring attractors in reinforcement learning systems
by Marcos Negre Saura, Richard Allmendinger, Wei Pan, Theodore Papamarkou
First submitted to arxiv on: 4 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper integrates ring attractors, a mathematical model inspired by neural circuit dynamics, into the Reinforcement Learning (RL) action selection process. Ring attractors serve as specialized brain-inspired structures that encode spatial information and uncertainty, improving learning speed and accuracy in RL. They facilitate organization of neural activity and enable distribution of spatial representations across the neural network in Deep Reinforcement Learning (DRL). The application involves mapping actions to specific locations on the ring and decoding the selected action based on neural activity. By building an exogenous model and integrating ring attractors into DRL agents, our approach significantly improves state-of-the-art performance on the Atari 100k benchmark, achieving a 53% increase in performance across selected baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper combines two ideas: “ring attractors” from brain science and “reinforcement learning” from AI. It tries to make machines learn better by using this brain idea. The goal is to help machines choose the best actions in situations where they need to consider different possibilities. The new approach works well on a big test, beating other methods that are already good at what they do. |
Keywords
» Artificial intelligence » Neural network » Reinforcement learning
