Jonathan Balloch

According to our database, Jonathan Balloch authored at least 4 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited.

Kenneth Eaton, Jonathan Balloch, Julia M. Kim, Mark O. Riedl

CoRR, 2024

External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling.

Rishav Bhagat, Jonathan Balloch, Zhiyu Lin, Julia Kim, Mark O. Riedl

CoRR, 2024

2021

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer.

James Seale Smith, Jonathan Balloch, Yen-Chang Hsu, Zsolt Kira

Proceedings of the International Joint Conference on Neural Networks, 2021

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning.

James Seale Smith, Yen-Chang Hsu, Jonathan Balloch, Yilin Shen, Hongxia Jin, Zsolt Kira

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021