Neuro-Symbolic World Models for Adapting to Open World Novelty

no code implementations • 16 Jan 2023 • Jonathan Balloch, Zhiyu Lin, Robert Wright, Xiangyu Peng, Mustafa Hussain, Aarun Srinivas, Julia Kim, Mark O. Riedl

Additionally, WorldCloner augments the policy learning process using imagination-based adaptation, where the world model simulates transitions of the post-novelty environment to help the policy adapt.

Decision Making reinforcement-learning +1

NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty

no code implementations • 23 Mar 2022 • Jonathan Balloch, Zhiyu Lin, Mustafa Hussain, Aarun Srinivas, Robert Wright, Xiangyu Peng, Julia Kim, Mark Riedl

We provide an ontology of for novelties most relevant to sequential decision making, which distinguishes between novelties that affect objects versus actions, unary properties versus non-unary relations, and the distribution of solutions to a task.

Decision Making reinforcement-learning +1