ML Anthology

Towards Robust, Efficient, and Practical Decision-Making: From Reward-Maximizing Deep Reinforcement Learning to Reward-Matching GFlowNets

Ling Pan
AAAI 2025 pp. 28724
doi:10.1609/AAAI.V39I27.35118 /aaai/2025/pan2025aaai-robust/

Abstract

In this talk, I will present our recent advances in sequential decision-making systems in reward-maximizing deep RL and the emerging reward-matching GFlowNets. The presentation will examine three fundamental challenges: efficiency, robustness, and practical applications.

PDF AAAI Semantic Scholar

Cite

Text

Pan. "Towards Robust, Efficient, and Practical Decision-Making: From Reward-Maximizing Deep Reinforcement Learning to Reward-Matching GFlowNets." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I27.35118

Markdown

[Pan. "Towards Robust, Efficient, and Practical Decision-Making: From Reward-Maximizing Deep Reinforcement Learning to Reward-Matching GFlowNets." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/pan2025aaai-robust/) doi:10.1609/AAAI.V39I27.35118

BibTeX

@inproceedings{pan2025aaai-robust,
  title     = {{Towards Robust, Efficient, and Practical Decision-Making: From Reward-Maximizing Deep Reinforcement Learning to Reward-Matching GFlowNets}},
  author    = {Pan, Ling},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {28724},
  doi       = {10.1609/AAAI.V39I27.35118},
  url       = {https://mlanthology.org/aaai/2025/pan2025aaai-robust/}
}