Summary of Highway Value Iteration Networks, by Yuhui Wang et al.
Highway Value Iteration Networks
by Yuhui Wang, Weida Li, Francesco Faccio, Qingyuan Wu, Jürgen Schmidhuber
First submitted to arxiv on: 5 Jun 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 In this paper, researchers develop a new type of neural network called the Highway Value Iteration Network (HVIN) to improve end-to-end learning for planning tasks. The HVIN combines value iteration networks with a differentiable “planning module” that approximates the value iteration algorithm. To enable long-term planning, the authors embed highway value iteration, a recent algorithm designed for credit assignment, into the VIN structure. This improved VIN has three additional components: an aggregate gate for skip connections, an exploration module to increase information flow, and a filter gate for safe exploration. The resulting HVIN can be trained using standard backpropagation with hundreds of layers. In long-term planning tasks requiring hundreds of planning steps, HVINs outperform traditional VINs and several advanced neural networks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make computers better at solving planning problems by creating a new kind of neural network called the Highway Value Iteration Network (HVIN). The HVIN is like a super-smart map that can help solve complex problems step-by-step. It does this by using something called value iteration, which is a way to figure out what’s the best thing to do next. The authors made this new kind of network better by adding special parts that help it learn and make good decisions. This means computers might be able to plan and solve problems even better than before. |
Keywords
» Artificial intelligence » Backpropagation » Neural network
