no code implementations • 2 Apr 2024 • Jonathan C. Balloch, Rishav Bhagat, Geigh Zollicoffer, Ruoran Jia, Julia Kim, Mark O. Riedl
However, the relationship between specific exploration characteristics and effective transfer learning in deep RL has not been characterized.
no code implementations • 12 Oct 2023 • Geigh Zollicoffer, Kenneth Eaton, Jonathan Balloch, Julia Kim, Mark O. Riedl, Robert Wright
We refer to the sudden change in visual properties or state transitions as novelties.
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.
no code implementations • 11 Oct 2022 • Jonathan C Balloch, Julia Kim, and Jessica L Inman, Mark O Riedl
The exploration--exploitation trade-off in reinforcement learning (RL) is a well-known and much-studied problem that balances greedy action selection with novel experience, and the study of exploration methods is usually only considered in the context of learning the optimal policy for a single learning task.
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.