TechRxiv
OODA_RL_Version_2.pdf (317.33 kB)
Download file

OODA-RL: A REINFORCEMENT LEARNING FRAMEWORK FOR ARTIFICIAL GENERAL INTELLIGENCE TO SOLVE OPEN WORLD NOVELTY

Download (317.33 kB)
preprint
posted on 28.12.2021, 19:03 by Pamul YadavPamul Yadav, Taewoo Kim, Ho Suk, Junyong Lee, Hyeonseong Jeong, Shiho Kim

Faster adaptability to open-world novelties by intelligent agents is a necessary factor in achieving the goal of creating Artificial General Intelligence (AGI). Current RL framework does not considers the unseen changes (novelties) in the environment. Therefore, in this paper, we have proposed OODA-RL, a Reinforcement Learning based framework that can be used to develop robust RL algorithms capable of handling both the known environments as well as adaptation to the unseen environments. OODA-RL expands the definition of internal composition of the agent as compared to the abstract definition in the classical RL framework, allowing the RL researchers to incorporate novelty adaptation techniques as an add-on feature to the existing SoTA as well as yet-to-be-developed RL algorithms.

History

Email Address of Submitting Author

pamul@yonsei.ac.kr

Submitting Author's Institution

Yonsei University

Submitting Author's Country

South Korea

Usage metrics

Licence

Exports