Recent Advances in Agent-Based Negotiation: Applications and Competition Challenges

Channel allocation in dense, decentralized Wi-Fi networks is a challenging due to the highly nonlinear solution space and the difficulty to estimate the opponent’s utility model. So far, only centralized or mediated approaches have succeeded in applying negotiation to this setting. We propose the first two fully-distributed negotiation approaches for Wi-Fi channel assignment. Both of them leverage a pre-sampling of the utility space with simulated annealing and a noisy estimation of the Wi-Fi utility function. Regarding negotiation protocols, one of the approaches makes use of the Alternating Offers protocol, while the other uses the novel Multiple Offers Protocol for Multilateral Negotiations with Partial Consensus (MOPaC), which naturally matches the problem peculiarities. We compare the performance of our proposed approaches with the previous mediated approach, based on simple text mediation. Our experiments show that our approaches yield better utility outcomes, better fairness and less information disclosure than the mediated approach.

One of serious threats on the Internet is a Distributed Reflective Denial-of-Service (DRDoS) attack. We are aiming to realize defenders that can deal with more sophisticated cooperative and strategic attacks which are becoming realistic and will be seen in the future. Specifically, we focus on an environment where there are attackers that can change their strategy of the DRDoS attacks in consideration of the alliance among the defenders, which we will require to develop the defenders which can give misleading information to fool the attackers about the recognition of alliance state and to coordinate their filtering strategy so that they utilize the current alliance among the defenders with maximum efficiency of the throughput for ordinary traffics. For achieving the final goal, we consider the simulation method of the DRDoS attacks including the attackers and the defenders that can respond dynamically according to the environment, and consider the method for building the environment. In our work, we also consider the DRDoS attackers that dynamically change their behavior, a method for a simulation in order to proceed the defenders’ Multi-Agent Reinforcement Learning (MARL) in an environment where there are the defenders against the attackers, the environment, and a MARL method to be applied there.

This paper introduces a dependency analysis and a categorization of conceptualized and existing economic decision support mechanisms for negotiation. The focus of our survey is on economic decision support mechanisms, although some behavioural support mechanisms were included, to recognize the important work in that area. We categorize support mechanisms from four different aspects: (i) economic versus behavioral decision support, (ii) analytical versus strategical support, (iii) active versus passive support and (iv) implicit versus explicit support. Our survey suggests that active mechanisms would be more effective than passive ones, and that implicit mechanisms can shield the user from mathematical complexities. Furthermore, we provide a list of existing economic support mechanisms.

This paper presents the negotiation support mechanisms provided by the Pocket Negotiator (PN) and an elaborate empirical evaluation of the economic decision support (EDS) mechanisms during the bidding phase of negotiations as provided by the PN. Some of these support mechanisms are offered actively, some passively. With passive support we mean that the user only gets that support by clicking a button, whereas active support is provided without prompting. Our results show, that PN improves negotiation outcomes, counters cognitive depletion, and encourages exploration of potential outcomes. We found that the active mechanisms were used more effectively than the passive ones and, overall, the various mechanisms were not used optimally, which opens up new avenues for research. As expected, the participants with higher negotiation skills outperformed the other groups, but still they benefited from PN support. Our experimental results show that people with enough technical skills and with some basic negotiation knowledge will benefit most from PN support. Our results also show that the cognitive depletion effect is reduced by Pocket Negotiator support. The questionnaire taken after the experiment shows that overall the participants found Pocket Negotiator easy to interact with, that it made them negotiate more quickly and that it improves their outcome. Based on our findings, we recommend to 1) provide active support mechanisms (push) to nudge users to be more effective, and 2) provide support mechanisms that shield the user from mathematical complexities.

An international competition for negotiating agents has been organized for years to facilitate research in agent-based negotiation and to encourage the design of negotiating agents that can operate in various scenarios. The 13th International Automated Negotiating Agents Competition (ANAC 2022) was held in conjunction with IJCAI2022. In ANAC2022, we had two leagues: Automated Negotiation League (ANL) and Supply Chain Management League (SCML). For the ANL, the participants designed a negotiation agent that can learn from the previous bilateral negotiation sessions it was involved in. In contrast, the research challenge was to make the right decisions to maximize the overall profit in a supply chain environment, such as determining with whom and when to negotiate. This chapter describes the overview of ANL and SCML in ANAC2022, and reports the results of each league, respectively.

The International Automated Negotiating Agent Competition introduces a new challenge each year to facilitate the research on agent-based negotiation and provide a test benchmark. ANAC 2020 addressed the problem of designing effective agents that do not know their users’ complete preferences in addition to their opponent’s negotiation strategy. Accordingly, this paper presents the negotiation strategy of the winner agent called “AhBuNe Agent”. The proposed heuristic-based bidding strategy checks whether it has sufficient orderings to reason about its complete preferences and accordingly decides whether to sacrifice some utility in return for preference elicitation. While making an offer, it uses the most-desired known outcome as a reference and modifies the content of the bid by adopting a concession-based strategy. By analyzing the content of the given ordered bids, the importance ranking of the issues is estimated. As our agent adopts a fixed time-based concession strategy and takes the estimated issue importance ranks into account, it determines to what extent the issues are to be modified. The evaluation results of the ANAC 2020 show that our agent beats the other participating agents in terms of the received individual score.

The success of a negotiation depends mainly on the strategies of the negotiators and the problem domain. It is common for negotiators to rely on an agenda to simplify the process and reach better deals. This is particularly true when the negotiators’ preferences are defined over multiple issues. Using an agenda to explore and decompose the interdependencies between the issues is one way to address this problem. This paper applies the classical divide-and-conquer approach to automated negotiations through utility decomposition and bottom-up agenda construction. The approach does not impose an agenda from the top level of the negotiations but builds it bottom-up, given the individual utility functions of the agents and the relationships between the issues. We implemented our method in a novel protocol called the Decomposable Alternating Offers Protocol (DAOP). The protocol reduces the cost of exploring the utility spaces of the agents and the generation of optimal bids. As a result, the divide-and-conquer algorithm positively influences the global performance of an automated negotiation system.

Automated negotiation agents usually rely on theories and principles from other fields to guide their concession behavior so that they can perform better when put into productive environments. For example, a marketing agent developed for automated trading could rely on financial theories. While introducing new theories, however, new parameters will be introduced to the agent’s concession mechanisms as well. This paper, shows a method for adjusting these parameters to construct a more powerful concession mechanisms. Experiments were done with the Supply Chain Management League (SCML) one-shot environment, and the results indicate that this method can actually improve the performance of agents which employ theories mainly from economic fields. Furthermore, the method can also help distinguish models that are inefficient or even have negative effects in certain situations.