Learning and Efficiency in Games with Dynamic Population (original) (raw)
Related papers
Multiplicative updates outperform generic no-regret learning in congestion games
Proceedings of the 41st annual ACM symposium on Symposium on theory of computing - STOC '09, 2009
We study the outcome of natural learning algorithms in atomic congestion games. Atomic congestion games have a wide variety of equilibria often with vastly differing social costs. We show that in almost all such games, the wellknown multiplicative-weights learning algorithm results in convergence to pure equilibria. Our results show that natural learning behavior can avoid bad outcomes predicted by the price of anarchy in atomic congestion games such as the load-balancing game introduced by Koutsoupias and Papadimitriou, which has super-constant price of anarchy and has correlated equilibria that are exponentially worse than any mixed Nash equilibrium.
Learning in games with unstable equilibria
2009
We propose a new concept for the analysis of games, the TASP, which gives a precise prediction about non-equilibrium play in games whose Nash equilibria are mixed and are unstable under fictitious play-like learning. We show that, when players learn using weighted stochastic fictitious play and so place greater weight on recent experience, the time average of play often converges in these ���unstable��� games, even while mixed strategies and beliefs continue to cycle.
Auctions Between Regret-Minimizing Agents
2021
We analyze a scenario in which software agents implemented as regret minimizing algorithms engage in a repeated auction on behalf of their users. We study first price and second price auctions, as well as their generalized versions (e.g., as those used for ad auctions). Using both theoretical analysis and simulations, we show that, surprisingly, in second price auctions the players have incentives to mis-report their true valuations to their own learning agents, while in the first price auction it is a dominant strategy for all players to truthfully report their valuations to their agents.
Automated Learning in Network Games
1998
We propose to study the design and implementation of automated agents suitable for controlling and optimizing resource allocation in large-scale networks. We begin with the standard assumptions of economics and game theory, which we generalize and enhance with a framework for logical reasoning. In this way, we create models applicable in more general economic settings, as well as in network contexts, which we intend to use to analyze the behavior of intelligent agents that abide by adaptive learning algorithms.
Learning and Acyclicity in the Market Game
2021
We show that strategic market games, the non-cooperative implementation of a matching with transfers or an assignment game, are weakly acyclic. This property ensures that many common learning algorithms will converge to Nash equilibria in these games, and that the allocation mechanism can therefore be decentralized. Convergence hinges on the appropriate price clearing rule and has different properties for betterand best-response dynamics. We tightly characterize the robustness of this convergence in terms of so-called schedulers for both types of dynamics.
A Learning Approach to Auctions
Journal of Economic Theory, 1998
We analyze a repeated first-price auction in which the types of the players are determined before the first round. It is proved that if every player is using either a belief-based learning scheme with bounded recall or a generalized fictitious play learning scheme, then after sufficiently long time, the players' bids are in equilibrium in the one-shot auction in which
Learning Equilibrium in Resource Selection Games
We consider a resource selection game with incomplete in- formation about the resource-cost functions. All the players know is the set of players, an upper bound on the possible costs, and that the cost functions are positive and nondecreas- ing. The game is played repeatedly and after every stage each player observes her cost, and the actions of all play- ers. For every > 0 we prove the existence of a learning -equilibrium, which is a profile of algorithms, one for each player such that a unilateral deviation of a player is, up to not beneficial for her regardless of the actual cost functions. Furthermore, the learning equilibrium yields an optimal so- cial cost.
2006
: We consider the problem of learning strategy selection in games. The theoretical solution to this problem is a distribution over strategies that responds to a Nash equilibrium of the game. When the payoff function of the game is not known to the participants, such a ...
Current Medical Research and Opinion, 2010
In this paper we explore how specific aspects of market transparency and agents’ behavior affect the efficiency of the market outcome. In particular, we are interested whether learning behavior with and without information about actions of other participants improves market efficiency. We consider a simple market for a homogeneous good populated by buyers and sellers. The valuations of the buyers and the costs of the sellers are given exogenously. Agents are involved in consecutive trading sessions, which are organized as a continuous double auction with order book. Using Individual Evolutionary Learning agents submit price bids and offers, trying to learn the most profitable strategy by looking at their realized and counterfactual or “foregone” payoffs. We find that learning outcomes heavily depend on information treatments. Under full information about actions of others, agents’ orders tend to be similar, while under limited information agents tend to submit their valuations/costs. This behavioral outcome results in higher price volatility for the latter treatment. We also find that learning improves allocative efficiency when compared to outcomes with Zero-Intelligent traders.
Adaptive learning under strategic and structural uncertainty: the case of auction games
2020
In games of incomplete information individual players make decisions facing a combination of structural uncertainty about the underlying parameters of the environment, and strategic uncertainty about the actions undertaken by their partners. How well are human actors able to cope with these uncertainties, and what models best describe their learning in such environments? We use a double auction task with different competitive and informational environments to characterize learning abilities of the single human participants (buyers) in a range of adaptive learning models covering reinforcement learning, directional learning and belief learning. Results show that real behaviour is best described using simple models of directional learning type with minimal knowledge assumptions about information efficiency of prices. This behavior is consistent with bounded rationality and risk aversion: human subjects try to maximize their chance for transaction, and do so using the simplest learning...