Stochastic and shortest path games: theory and algorithms

By S. Patek. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

RUDDER: Return Decomposition for Delayed Rewards (2018, background): “(A87) In Stephen Patek’s PhD thesis, [82] Lemma 5.”
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms (2019, background): “, [230, 231, 232, 233, 234], for different variants of such Markov games.”
A Theoretical Analysis of Deep Q-Learning (2019, background): “By the von Neumann’s minimax theorem (Von Neumann and Morgenstern, 1947; Patek, 1997), there exists a minimax function of the game, Q∗ : S × A× B → R, such that Q(s, a, b) = max π min ν Q(s, a, b) = min ν max π Q(s, a, b).”
Robust Adversarial Reinforcement Learning (2017, background): “(Perolat et al., 2015; Patek, 1997) show that notions of minimax equilibrium and Nash equilibrium are equivalent for this game with optimal equilibrium reward: However solutions to ﬁnding the Nash equilibria strategies often involve greedily solving N minimax equilibria for a zero-sum matrix game,…”
Action Robust Reinforcement Learning and Applications in Continuous Control (2019, methodology): “A MG is determined by the 5-tuple (S,A,B, P,R, γ) (Patek, 1997).”