Designing an effective and intelligent bidding strategy is one of the most compelling research challenges in automated negotiation, where software agents negotiate with each other to find a mutual agreement when there is a conflict of interests. Instead of designing a hand-crafted decision-making module, this work proposes a novel bidding strategy adopting an actor-critic reinforcement learning approach, which learns what to offer in a bilateral negotiation. An entropy reinforcement learning framework called Soft Actor-Critic (SAC) is applied to the bidding problem, and a self-play approach is employed to train the model. Our model learns to produce the target utility of the coming offer based on previous offer exchanges and remaining time. Furthermore, an imitation learning approach called behavior cloning is adopted to speed up the learning process. Also, a novel reward function is introduced that does take not only the agent’s own utility but also the opponent’s utility at the end of the negotiation. The developed agent is empirically evaluated. Thus, a large number of negotiation sessions are run against a variety of opponents selected in different domains varying in size and opposition. The agent’s performance is compared with its opponents and the performance of the baseline agents negotiating with the same opponents. The empirical results show that our agent successfully negotiates against challenging opponents in different negotiation scenarios without requiring any former information about the opponent or domain in advance. Furthermore, it achieves better results than the baseline agents regarding the received utility at the end of the successful negotiations.

Specifying a normative multiagent system (nMAS) is challenging, because different agents often have conflicting requirements. Whereas existing approaches can resolve clear-cut conflicts, tradeoffs might occur in practice among alternative nMAS specifications with no apparent resolution. To produce an nMAS specification that is acceptable to each agent, we model the specification process as a negotiation over a set of norms. We propose an agent-based negotiation framework, where agents' requirements are represented as values (e.g., patient safety, privacy, and national security), and an agent revises the nMAS specification to promote its values by executing a set of norm revision rules that incorporate ontology-based reasoning. To demonstrate that our framework supports creating a transparent and accountable nMAS specification, we conduct an experiment with human participants who negotiate against our agent. Our findings show that our negotiation agent reaches better agreements (with small p-value and large effect size) faster than a baseline strategy. Moreover, participants perceive that our agent enables more collaborative and transparent negotiations than the baseline (with small p-value and large effect size in particular settings) toward reaching an agreement.