We consider multi-agent systems whose agents compete for resources by striving to be in the minority group. The agents adapt to the environment by reinforcement learning of the preferences of the policies they hold. Diversity of preferences of policies is introduced by adding random biases to the initial cumulative payoffs of their policies. We explain and provide evidence that agent cooperation becomes increasingly important when diversity increases. Analyses of these mechanisms yield excellent agreement with simulations over nine decades of data.

We propose a new set of criteria for learning algorithms in multi-agent systems, one that is more stringent and (we argue) better justified than previous proposed criteria. Our criteria, which apply most straightforwardly in repeated games with average rewards, consist of three requirements: (a) against a specified class of opponents (this class is a parameter of the criterion) the algorithm yield a payoff that approaches the payoff of the best response, (b) against other opponents the algorithm's payoff at least approach (and possibly exceed) the security level payoff (or maximin value), and (c) subject to these requirements, the algorithm achieve a close to optimal payoff in self-play. We furthermore require that these average payoffs be achieved quickly. We then present a novel algorithm, and show that it meets these new criteria for a particular parameter class, the class of stationary opponents. Finally, we show that the algorithm is effective not only in theory, but also empirically. Using a recently introduced comprehensive game theoretic test suite, we show that the algorithm almost universally outperforms previous learning algorithms.

Learning in a multiagent system is a challenging problem due to two key factors. First, if other agents are simultaneously learning then the environment is no longer stationary, thus undermining convergence guarantees. Second, learning is often susceptible to deception, where the other agents may be able to exploit a learner's particular dynamics. In the worst case, this could result in poorer performance than if the agent was not learning at all. These challenges are identifiable in the two most common evaluation criteria for multiagent learning algorithms: convergence and regret.

We consider multi-agent systems whose agents compete for resources by striving to be in the minority group. The agents adapt to the environment by reinforcement learning of the preferences of the policies they hold. Diversity of preferences of policies is introduced by adding random biases tothe initial cumulative payoffs of their policies. We explain and provide evidence that agent cooperation becomes increasingly important when diversity increases. Analyses of these mechanisms yield excellent agreement with simulations over nine decades of data.

We propose a new set of criteria for learning algorithms in multi-agent systems, one that is more stringent and (we argue) better justified than previous proposed criteria. Our criteria, which apply most straightforwardly inrepeated games with average rewards, consist of three requirements: (a) against a specified class of opponents (this class is a parameter of the criterion) the algorithm yield a payoff that approaches the payoff of the best response, (b) against other opponents the algorithm's payoff at least approach (and possibly exceed) the security level payoff (or maximin value),and (c) subject to these requirements, the algorithm achieve a close to optimal payoff in self-play. We furthermore require that these average payoffs be achieved quickly. We then present a novel algorithm, and show that it meets these new criteria for a particular parameter class, the class of stationary opponents. Finally, we show that the algorithm is effective not only in theory, but also empirically. Using a recently introduced comprehensive game theoretic test suite, we show that the algorithm almost universally outperforms previous learning algorithms.

Learning in a multiagent system is a challenging problem due to two key factors. First, if other agents are simultaneously learning then the environment isno longer stationary, thus undermining convergence guarantees. Second, learning is often susceptible to deception, where the other agents may be able to exploit a learner's particular dynamics. In the worst case, this could result in poorer performance than if the agent was not learning at all. These challenges are identifiable in the two most common evaluationcriteria for multiagent learning algorithms: convergence and regret. Algorithms focusing on convergence or regret in isolation are numerous. In this paper, we seek to address both criteria in a single algorithm by introducing GIGA-WoLF, a learning algorithm for normalform games.We prove the algorithm guarantees at most zero average regret, while demonstrating the algorithm converges in many situations of self-play. We prove convergence in a limited setting and give empirical resultsin a wider variety of situations. These results also suggest a third new learning criterion combining convergence and regret, which we call negative non-convergence regret (NNR).

Online mechanism design (OMD) addresses the problem of sequential decision making in a stochastic environment with multiple self-interested agents. The goal in OMD is to make value-maximizing decisions despite this self-interest. In previous work we presented a Markov decision process (MDP)-basedapproach to OMD in large-scale problem domains. In practice the underlying MDP needed to solve OMD is too large and hence the mechanism must consider approximations. This raises the possibility thatagents may be able to exploit the approximation for selfish gain. We adopt sparse-sampling-based MDP algorithms to implement ɛ- efficient policies, and retain truth-revelation as an approximate Bayesian-Nash equilibrium. Our approach is empirically illustrated in the context of the dynamic allocation of WiFi connectivity to users in a coffeehouse.

Most autonomous robots are equipped with restricted, unreliable, and inaccurate sensors and effectors and operate in complex and dynamic environments. A successful approach to deal with the resulting uncertainty is the use of controllers that prescribe the robots' behavior in terms of concurrent reactive plans (CRPs) -- plans that specify how the robots are to react to sensory input in order to accomplish their jobs reliably (e.g., McDermott, 1992a; Beetz, 1999). Reactive plans are successfully used to produce situation specific behavior, to detect problems and recover from them automatically, and to recognize and exploit opportunities (Beetz et al., 2001). These kinds of behaviors are particularly important for autonomous robots that have only uncertain information about the world, act in dynamically changing environments, and are to accomplish complex tasks efficiently. Besides reliability and flexibility, foresight is another important capability of competent autonomous robots (McDermott, 1992a).

AI and AAAI are coevolving. As AI matures, its focus is shifting from inward-looking to outwardlooking. Some of the new concerns of the field are social awareness, networking, cross-disciplinarity, globalization, and open access. AAAI must reflect and support those concerns. AI is now a mature discipline.

Wasps, bees, ants and termites all make effective use of their environment and resources by displaying collective "swarm" intelligence. Termite colonies - for instance - build nests with a complexity far beyond the comprehension of the individual termite, while ant colonies dynamically allocate labor to various vital tasks such as foraging or defense without any central decision-making ability. Recent research suggests that microbial life can be even richer: highly social, intricately networked, and teeming with interactions, as found in bacteria. What strikes from these observations is that both ant colonies and bacteria have similar natural mechanisms based on Stigmergy and Self-Organization in order to emerge coherent and sophisticated patterns of global foraging behavior. Keeping in mind the above characteristics we propose a Self-Regulated Swarm (SRS) algorithm which hybridizes the advantageous characteristics of Swarm Intelligence as the emergence of a societal environmental memory or cognitive map via collective pheromone laying in the landscape (properly balancing the exploration/exploitation nature of our dynamic search strategy), with a simple Evolutionary mechanism that trough a direct reproduction procedure linked to local environmental features is able to self-regulate the above exploratory swarm population, speeding it up globally.