Summary of Navigation with Qphil: Quantizing Planner For Hierarchical Implicit Q-learning, by Alexi Canesse et al.
Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning
by Alexi Canesse, Mathieu Petitbois, Ludovic Denoyer, Sylvain Lamprier, Rémy Portelas
First submitted to arxiv on: 12 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO)
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 transformer-based approach to Offline Reinforcement Learning (RL) is presented, addressing the signal-to-noise ratio challenge by leveraging a learned quantizer of the space. This enables training of a simpler zone-conditioned low-level policy and simplifies planning through discrete autoregressive prediction. The approach achieves state-of-the-art results in complex long-distance navigation environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Offline RL is a powerful alternative to imitation learning, but it’s limited by incorrect policy updates due to errors in value estimates. Hierarchical methods decouple high-level path planning from low-level path following. A new transformer-based planner uses a learned quantizer of the space to enable zone-conditioned reasoning and explicit trajectory stitching. |
Keywords
» Artificial intelligence » Autoregressive » Reinforcement learning » Transformer
