Summary of Learning Constraint Network From Demonstrations Via Positive-unlabeled Learning with Memory Replay, by Baiyu Peng et al.
Learning Constraint Network from Demonstrations via Positive-Unlabeled Learning with Memory Replay
by Baiyu Peng, Aude Billard
First submitted to arxiv on: 23 Jul 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 This paper proposes a positive-unlabeled (PU) learning approach to infer continuous, arbitrary, and possibly nonlinear constraints from expert demonstrations. The method learns a sub-optimal policy to generate high-reward-winning but potentially infeasible trajectories, which serve as unlabeled data containing both feasible and infeasible states. A feasible-infeasible classifier (i.e., constraint model) is learned through a postprocessing PU learning technique. The entire method employs an iterative framework alternating between updating the policy and updating the constraint model. Additionally, a memory buffer is introduced to record and reuse samples from previous iterations to prevent forgetting. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps robots learn how to follow rules in different situations by watching experts do it. Usually, these rules are unknown or hard to specify accurately. The researchers created a new way to figure out the rules from expert demonstrations, even if they’re complex or non-linear. They tested their method on two robotic environments and showed that it can accurately infer constraints and create safe policies. |
