The Markov game (also called stochastic game (Filar & Vrieze 1997)) has been adopted as a theoretical framework for multiagent reinforcement learning (Littman 1994). In a Markov game, there are n agents, each facing a Markov decision process (MDP). All agents’ MDPs are correlated through their reward functions and the state transition function. As Markov decision process provides a theoretical ...

In this paper, a new iteration approach is derived to solve the optimal strategies for quadratic zero-sum game of finite-horizon continuous-time nonaffine nonlinear system. Through iteration algorithm between two sequences which are a sequence of state trajectories of linear quadratic zero-sum games and a sequence of corresponding Riccati differential equations, the optimal strategies for the n...

Strictly competitive games are a class of 2-player games often quoted in the literature to be a proper generalization of zero-sum games. Other times it is claimed, e.g. by Aumann, that strictly competitive games are only payoff transformations of zero-sum games. But to the best of our knowledge there is no proof of such claim. We shed light to this point of confusion in the literature, showing ...

Data-free quantization (DFQ) recovers the performance of quantized network (Q) without accessing real data, but generates fake sample via a generator (G) by learning from full-precision (P) instead. However, such generation process is totally independence Q, specialized as failing to consider adaptability generated samples, i.e., beneficial or adversarial, over resulting into non-ignorable loss...

The slow-coloring game is played by Lister and Painter on a graph G. On each round, Lister marks a nonempty subsetM of the uncolored vertices, scoring ∣M ∣ points. Painter then gives a color to a subset of M that is independent in G. The game ends when all vertices are colored. Painter and Lister want to minimize and maximize the total score, respectively. The best score that each player can gu...

(3) f(x) = (log x/log 2) + 0(1)? 1\Mloser and I asked : Is it true that f(2 11) >_ k+2 for sufficiently large k? Conway and Guy showed that the answer is affirmative (unpublished) . P. Erdös, Problems and results in additive number theory, Colloque, Théorie des Nombres, Bruxelles 1955, p . 137 . 2. Let 1 < a 1< . . . < ak <_ x be a sequence of integers so that all the sums ai,+ . . .+ais, i 1 <...