DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces

Pranavi Pathakota, Hardik Meisheri, Harshad Khadilkar. DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces. In Mehdi Dastani, Jaime Simão Sichman, Natasha Alechina, Virginia Dignum, editors, Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, May 6-10, 2024. pages 2411-2413, ACM, 2024. [doi]

Abstract

Abstract is missing.