Stochastic Games*
By Lloyd S. Shapley. 1953
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Michael L. Littman
- Michael H. Bowling
- Craig Boutilier
- Scott Sanner
- Sven Gronauer
- Karl Tuyls
- Diederik Marijn Roijers
- Peter Stone
Citations in the corpus
- Generalized Markov Decision Processes: Dynamic-programming and Reinforcement-learning Algorithms (1996, methodology): “Generalized mdps provide a foundation for decision making in mdps and games, as well as in risk-sensitive models [15], exploration-sensitive models [20, 36], simultaneous-action games [39], and other models.”
- Multi-objective multi-agent decision making: a utility-based analysis and survey (2019, background): “Multi-agent decision making problems can often be modelled as a stochastic (or Markov) game (SG) [102,121].”
- Empirical Dynamic Programming (2013, background): “We call T the Shapley operator in honor of Shapley who first introduced it [39].”
- Practical solution techniques for first-order MDPs (2009, background): “Markov decision processes (MDPs) were first introduced and developed in the fields of operations research and economics (Bellman, 1957; Shapley, 1953; Howard, 1960).”
- Multi-agent deep reinforcement learning: a survey (2021, background): “These games are also known 1 Markov games are also known as Stochastic Games (Shapley 1953), but we continue to use the term Markov Game to draw a clear distinction between deterministic Markov Games and stochastic Markov Games.”
- Two-player nonZero–sum stopping games in discrete time (2004, unknown): “tage l. Formally, G(k,l) is a stopping game in which the terminal payoff at stage n is equal to the terminal payoff at stage k +(nmodl−k) in Γ. This periodicgame is a simple stochastic game [see, e.g., Shapley (1953) or Flesch, Thvijsman and Vrieze (1996)] and isknown to admit an ε-equilibrium in peri”
- Distributionally Robust Markov Decision Processes (2010, unknown): “, Sion [32], Karlin [22], Shapley [31]).”
- Convergence and No-Regret in Multiagent Learning (2004, background): “When a learner is placed in the context of games with state, such as stochastic games (Shapley, 1953), estimating the value of a state is critical.”