Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory

no code implementations • 24 Aug 2023 • Karthik Somayaji NS, Yu Wang, Malachi Schram, Jan Drgona, Mahantesh Halappanavar, Frank Liu, Peng Li

Our work proposes to enhance the resilience of RL agents when faced with very rare and risky events by focusing on refining the predictions of the extreme values predicted by the state-action value function distribution.

reinforcement-learning Reinforcement Learning (RL)

AutoNF: Automated Architecture Optimization of Normalizing Flows Using a Mixture Distribution Formulation

no code implementations • 29 Sep 2021 • Yu Wang, Jan Drgona, Jiaxin Zhang, Karthik Somayaji NS, Frank Y Liu, Malachi Schram, Peng Li

Although various flow models based on different transformations have been proposed, there still lacks a quantitative analysis of performance-cost trade-offs between different flows as well as a systematic way of constructing the best flow architecture.