FIELD NOTES TOPIC
reward learning
2 notes, newest first.
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
The research paper proposes a method for teaching machines to learn robust reward functions that can work across various operational contexts. The study focuses on scenarios with diverse feedback modalities and…
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
The researchers introduce a machine teaching algorithm that operates across multiple MDPs (multi-agent decision making problems) to learn robust reward functions from heterogeneous feedback modalities in diverse…
