Negotiation is a crucial ability in human communication. Recently, there has been a resurgent research interest in negotiation dialogue systems, whose goal is to create intelligent agents that can assist people in resolving conflicts or reaching agreements. Although there have been many explorations into negotiation dialogue systems, a systematic review of this task has not been performed to date. We aim to fill this gap by investigating recent studies in the field of negotiation dialogue systems, and covering benchmarks, evaluations and methodologies within the literature. We also discuss potential future directions, including multi-modal, multi-party and cross-cultural negotiation scenarios. Our goal is to provide the community with a systematic overview of negotiation dialogue systems and to inspire future research.

The increasing prevalence of multi-agent learning systems in society necessitates understanding how to learn effective and safe policies in general-sum multi-agent environments against a variety of opponents, including self-play. General-sum learning is difficult because of non-stationary opponents and misaligned incentives. Our first main contribution is to show that many recent approaches to general-sum learning can be derived as approximations to Stackelberg strategies, which suggests a framework for developing new multi-agent learning algorithms. We then define non-coincidental games as games in which the Stackelberg strategy profile is not a Nash Equilibrium. This notably includes several canonical matrix games and provides a normative theory for why existing algorithms fail in self-play in such games. We address this problem by introducing Welfare Equilibria (WE) as a generalisation of Stackelberg Strategies, which can recover desirable Nash Equilibria even in non-coincidental games. Finally, we introduce Welfare Function Search (WelFuSe) as a practical approach to finding desirable WE against unknown opponents, which finds more mutually desirable solutions in self-play, while preserving performance against naive learning opponents.

In this paper, we focus on single-demonstration imitation learning (IL), a practical approach for real-world applications where obtaining numerous expert demonstrations is costly or infeasible. In contrast to typical IL settings with multiple demonstrations, single-demonstration IL involves an agent having access to only one expert trajectory. We highlight the issue of sparse reward signals in this setting and propose to mitigate this issue through our proposed Transition Discriminator-based IL (TDIL) method. TDIL is an IRL method designed to address reward sparsity by introducing a denser surrogate reward function that considers environmental dynamics. This surrogate reward function encourages the agent to navigate towards states that are proximal to expert states. In practice, TDIL trains a transition discriminator to differentiate between valid and non-valid transitions in a given environment to compute the surrogate rewards. The experiments demonstrate that TDIL outperforms existing IL approaches and achieves expert-level performance in the single-demonstration IL setting across five widely adopted MuJoCo benchmarks as well as the "Adroit Door" environment.

Reliable predictions of critical phenomena, such as weather, wildfires and epidemics are often founded on models described by Partial Differential Equations (PDEs). However, simulations that capture the full range of spatio-temporal scales in such PDEs are often prohibitively expensive. Consequently, coarse-grained simulations that employ heuristics and empirical closure terms are frequently utilized as an alternative. We propose a novel and systematic approach for identifying closures in under-resolved PDEs using Multi-Agent Reinforcement Learning (MARL). The MARL formulation incorporates inductive bias and exploits locality by deploying a central policy represented efficiently by Convolutional Neural Networks (CNN). We demonstrate the capabilities and limitations of MARL through numerical solutions of the advection equation and the Burgers' equation. Our results show accurate predictions for in- and out-of-distribution test cases as well as a significant speedup compared to resolving all scales.

This paper introduces a user-friendly platform developed by the University of Kentucky Center for Applied AI, designed to make large, customized language models (LLMs) more accessible. By capitalizing on recent advancements in multi-LoRA inference, the system efficiently accommodates custom adapters for a diverse range of users and projects. The paper outlines the system's architecture and key features, encompassing dataset curation, model training, secure inference, and text-based feature extraction. We illustrate the establishment of a tenant-aware computational network using agent-based methods, securely utilizing islands of isolated resources as a unified system. The platform strives to deliver secure LLM services, emphasizing process and data isolation, end-to-end encryption, and role-based resource authentication. This contribution aligns with the overarching goal of enabling simplified access to cutting-edge AI models and technology in support of scientific discovery.

Shielding is a popular technique for achieving safe reinforcement learning (RL). However, classical shielding approaches come with quite restrictive assumptions making them difficult to deploy in complex environments, particularly those with continuous state or action spaces. In this paper we extend the more versatile approximate model-based shielding (AMBS) framework to the continuous setting. In particular we use Safety Gym as our test-bed, allowing for a more direct comparison of AMBS with popular constrained RL algorithms. We also provide strong probabilistic safety guarantees for the continuous setting. In addition, we propose two novel penalty techniques that directly modify the policy gradient, which empirically provide more stable convergence in our experiments.

Agent-based models (ABMs) have shown promise for modelling various real world phenomena incompatible with traditional equilibrium analysis. However, a critical concern is the manual definition of behavioural rules in ABMs. Recent developments in multi-agent reinforcement learning (MARL) offer a way to address this issue from an optimisation perspective, where agents strive to maximise their utility, eliminating the need for manual rule specification. This learning-focused approach aligns with established economic and financial models through the use of rational utility-maximising agents. However, this representation departs from the fundamental motivation for ABMs: that realistic dynamics emerging from bounded rationality and agent heterogeneity can be modelled. To resolve this apparent disparity between the two approaches, we propose a novel technique for representing heterogeneous processing-constrained agents within a MARL framework. The proposed approach treats agents as constrained optimisers with varying degrees of strategic skills, permitting departure from strict utility maximisation. Behaviour is learnt through repeated simulations with policy gradients to adjust action likelihoods. To allow efficient computation, we use parameterised shared policy learning with distributions of agent skill levels. Shared policy learning avoids the need for agents to learn individual policies yet still enables a spectrum of bounded rational behaviours. We validate our model's effectiveness using real-world data on a range of canonical $n$-agent settings, demonstrating significantly improved predictive capability.

Many real-world applications involve some agents that fall into two teams, with payoffs that are equal within the same team but of opposite sign across the opponent team. The so-called two-team zero-sum Markov games (2t0sMGs) can be resolved with reinforcement learning in recent years. However, existing methods are thus inefficient in light of insufficient consideration of intra-team credit assignment, data utilization and computational intractability. In this paper, we propose the individual-global-minimax (IGMM) principle to ensure the coherence between two-team minimax behaviors and the individual greedy behaviors through Q functions in 2t0sMGs. Based on it, we present a novel multi-agent reinforcement learning framework, Factorized Multi-Agent MiniMax Q-Learning (FM3Q), which can factorize the joint minimax Q function into individual ones and iteratively solve for the IGMM-satisfied minimax Q functions for 2t0sMGs. Moreover, an online learning algorithm with neural networks is proposed to implement FM3Q and obtain the deterministic and decentralized minimax policies for two-team players. A theoretical analysis is provided to prove the convergence of FM3Q. Empirically, we use three environments to evaluate the learning efficiency and final performance of FM3Q and show its superiority on 2t0sMGs.

One of the most important challenges of Smart City Applications is to adapt the system to interact with non-expert users. Robot imitation frameworks aim to simplify and reduce times of robot programming by allowing users to program directly through demonstrations. In classical frameworks, actions are modeled using joint or Cartesian space trajectories. Other features, such as visual ones, are not always well represented with these pure geometrical approaches. Continuous Goal-Directed Actions (CGDA) is an alternative to these methods, as it encodes actions as changes of any feature that can be extracted from the environment. As a consequence of this, the robot joint trajectories for execution must be fully computed to comply with this feature-agnostic encoding. This is achieved using Evolutionary Algorithms (EA), which usually requires too many evaluations to perform this evolution step in the actual robot. Current strategies involve performing evaluations in a simulation, transferring the final joint trajectory to the actual robot. Smart City applications involve working in highly dynamic and complex environments, where having a precise model is not always achievable. Our goal is to study the tractability of performing these evaluations directly in a real-world scenario. Two different approaches to reduce the number of evaluations using EA, are proposed and compared. In the first approach, Particle Swarm Optimization (PSO)-based methods have been studied and compared within CGDA: naive PSO, Fitness Inheritance PSO (FI-PSO), and Adaptive Fuzzy Fitness Granulation with PSO (AFFG-PSO). The second approach studied the introduction of geometrical and velocity constraints within CGDA. The effects of both approaches were analyzed and compared in the wax and paint actions, two CGDA commonly studied use cases. Results from this paper depict an important reduction in the number of evaluations.

We present a simple argument using Promise Theory and dimensional analysis for the Dunbar scaling hierarchy, supported by recent data from group formation in Wikipedia editing. We show how the assumption of a common priority seeds group alignment until the costs associated with attending to the group outweigh the benefits in a detailed balance scenario. Subject to partial efficiency of implementing promised intentions, we can reproduce a series of compatible rates that balance growth with entropy.