A feature-based Q-learning method for risk-averse finite-horizon MDPs using newly defined mini-batch coherent risk measures and multipattern Q-factor approximation achieves a regret bound of O(H² N^H √K).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation
A feature-based Q-learning method for risk-averse finite-horizon MDPs using newly defined mini-batch coherent risk measures and multipattern Q-factor approximation achieves a regret bound of O(H² N^H √K).