Distributed Dynamic Reinforcement of Efficient Outcomes in Multiagent Coordination and Network Formation

We propose a simple payoff-based learning rule that is completely decentralized, and that leads to an efficient configuration of actions in any n-person finite strategic-form game with generic payoffs.The algorithm follows the theme of exploration versus exploitation and is hence stochastic in nature.We prove that if all agents adhere to this algorithm, then the agents will select the action profile that maximizes the sum of the agents' payoffs a high percentage of time. The algorithm requires no communication. Agents respond solely to changes in their own realized payoffs, which are affected by the actions of other agents in the system in ways that they do not necessarily understand. The method can be applied to the optimization of complex systems with many distributed components, such as the routing of information in networks and the design and control of wind farms. The proof of the proposed learning algorithm relies on the theory of large deviations for perturbed Markov chains.

show abstract

“…Game theory has important applications to the design and control of multiagent systems [1]- [9]. This design choice requires two steps.…”

Section: Introductionmentioning

confidence: 99%

Achieving Pareto Optimality Through Distributed Learning

Marden¹,

Young²,

Pao³

2014

SIAM J. Control Optim.

106

171

View full text Add to dashboard Cite

show abstract

“…To this end, we employ a learning framework (namely, perturbed learning automata) that is based on the reinforcement learning algorithm introduced by the authors in [6,7]. It belongs to the general class of learning automata [13].…”

Section: Reinforcement Learning (Rl)mentioning

confidence: 99%

Efficient Dynamic Pinning of Parallelized Applications by Reinforcement Learning with Applications

Chasparis

Rossbory

Janjić

2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. This paper introduces a resource allocation framework specifically tailored for addressing the problem of dynamic placement (or pinning) of parallelized applications to processing units. Decisions are updated recursively for each thread by a resource manager/scheduler which runs in parallel to the application's threads and periodically records their performances and assigns to them new CPU affinities. For updating the CPU-affinities, the scheduler uses a reinforcement-learning algorithm, each branch of which is responsible for assigning a new placement strategy to each thread. The proposed resource allocation framework is flexible enough to address alternative optimization criteria, such as maximum average processing speed and minimum speed variance among threads. We demonstrate the response of the dynamic scheduler under fixed and varying availability of resources (e.g., when other applications running on the same platform) in a parallel implementation of the Ant-Colony Optimization.

show abstract

“…The concept is inspired by classical methods in feedback control as well as the psychological tendency to extrapolate from past trends. Anticipatory learning was utilized in [3,20,21], where it was shown how anticipatory learning can alter the convergence to both mixed and pure equilibria.…”

Section: Smoothed Payoff Modificationmentioning

confidence: 99%

Population Games, Stable Games, and Passivity

Fox

Shamma

2013

Games

View full text Add to dashboard Cite

The class of "stable games", introduced by Hofbauer and Sandholm in 2009, has the attractive property of admitting global convergence to equilibria under many evolutionary dynamics. We show that stable games can be identified as a special case of the feedback-system-theoretic notion of a "passive" dynamical system. Motivated by this observation, we develop a notion of passivity for evolutionary dynamics that complements the definition of the class of stable games. Since interconnections of passive dynamical systems exhibit stable behavior, we can make conclusions about passive evolutionary dynamics coupled with stable games. We show how established evolutionary dynamics qualify as passive dynamical systems. Moreover, we exploit the flexibility of the definition of passive dynamical systems to analyze generalizations of stable games and evolutionary dynamics that include forecasting heuristics as well as certain games with memory.

show abstract

Distributed Dynamic Reinforcement of Efficient Outcomes in Multiagent Coordination and Network Formation

Cited by 30 publications

References 41 publications

Achieving Pareto Optimality Through Distributed Learning

Achieving Pareto Optimality Through Distributed Learning

Efficient Dynamic Pinning of Parallelized Applications by Reinforcement Learning with Applications

Population Games, Stable Games, and Passivity

Contact Info

Product

Resources

About