Leveraging Cross-Task Transfer in Sequential Decision Problems

KR Zentner - 2024 - search.proquest.com
The past few years have seen an explosion of interest in using machine learning to make
robots capable of learning a diverse set of tasks. These robots use Reinforcement Learning …

Successor Representations Enable Emergent Compositional Instruction Following

V Myers, C Zheng, A Dragan, K Fang… - 2nd CoRL Workshop on … - openreview.net
Effective task representations should facilitate compositionality, such that after learning a
variety of basic tasks, an agent can perform compound tasks consisting of multiple steps …

Towards Scalable Circuit Partitioning in Multi-Core Quantum Architectures with Graph Reinforcement Learning

A Esteban Márquez - 2024 - upcommons.upc.edu
Quantum computers present an undeniable potential to solve classically intractable
problems. However, the scalability of quantum architectures remains a principal challenge …