In an artificial society where agents repeatedly interact with one another, achieving high level of social utility is generally a challenge. This is especially true when the participating agents are self-interested, and that there is no central authority to coordinate, and direct communication or negotiation are not possible. Recently, Hao and Leung studied a new game theoretic approach, where a new type of repeated game as well as a new reinforcement learning based agent learning method were proposed. In particular, their game mechanism differs from traditional repeated games in that the agents are anonymous, and the agents interact with randomly chosen opponents. Their learning mechanism allows agents to coordinate without negotiations. Despite the promising initial results, however, extended simulation reveals that the outcomes are not stable in the long run, as the high level of cooperation is eventually not sustainable. In this work, we revisit the problem and propose a new learning mechanism as follows. First, we propose an enhanced Q-learning-based framework that allows the agents to better capture both the individual and social utilities that they have learned through observations. Second, we propose a new concept of "social attitude" for determining the action of the agents throughout the game. Simulation results reveal that this approach can achieve higher social utility, including close-to-optimal results in some scenarios, and more importantly, the results seem to be sustainable.

It is challenging to design effective scheduling algorithms for multimedia transmissions over wireless channels that employ adaptive modulation and coding (AMC). On the one hand, it is desirable for the overall system throughput to be enhanced by taking advantage of multi-user diversity. On the other hand, fairness or QoS guarantees need to be maintained for individual users, especially in the case of multimedia applications that have strict delay requirements. In this paper, we propose a novel scheduling algorithm called QoS-based cross-layer scheduling (QoS-CLS) to achieve a good design tradeoff. To maximize the system throughput, the algorithm takes into account the information on both the physical layer and the data link layer to schedule user transmissions. Using cross-layer information, the scheduling problem is formulated as a Markov Decision Process and the optimal decision policy (based on the channel status, traffic state, and buffer status of each traffic flow) is pre-calculated by linear programming. This policy is then stored in the system for scheduling in real-time. Simulation results show that QoS-CLS can greatly enhance the channel throughput compared to existing algorithms because of its cross-layer QoS consideration and the optimization method. Moreover, it can provide QoS guarantees while achieving efficient resource sharing among different traffic flows.

Online buyer coalition formation problem is an application of e-commerce and distributed agent technology. Most existing works in this topic involve social utility based approaches that assume the agents' utilities to be transferable. However, we argue that there are situations where the transferable utility model is not well suited for the problem, and that coalition stability is a more important solution concept than social utility. In this paper, we study the problem from a non-transferable utility approach where the focus is on achieving stable solutions in term of the core and Pare to efficiency. A new distributed mechanism is proposed where agents are allowed to propose incremental improvements toward a stable solution. We show by experiment that our mechanism is able to reach core-stable solutions in over 99% of the cases, which suggests a big improvement over the existing approaches.