Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation

Tonghe Zhang; Yu Chen; Longbo Huang

2024 ICML ICML 2024

Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Tonghe Zhang, Yu Chen, Longbo Huang

Topics

Artificial Intelligence > Core AI > Planning Machine Learning > Optimization & Theory > Learning Theory Reinforcement Learning > Methods > Model-Based RL

Keywords

regret analysis partially observable markov decision process risk-sensitive reinforcement learning entropic risk measure beta vectors hindsight observation

Download PDF