In this paper, a Priority-based Dynamic REsource Allocation with decentralized Multi-task assignment (P-DREAM) approach is presented to protect a territory from highly manoeuvring intruders. In the first part, static optimization problems are formulated to compute the following parameters of the perimeter defense problem; the number of reserve stations, their locations, the priority region, the monitoring region, and the minimum number of defenders required for the monitoring purpose. The concept of a prioritized intruder is proposed here to identify and handle those critical intruders (computed based on the velocity ratio and location) to be tackled on a priority basis. The computed priority region helps to assign reserve defenders sufficiently earlier such that they can neutralize the prioritized intruders. The monitoring region defines the minimum region to be monitored and is sufficient enough to handle the intruders. In the second part, the earlier developed DREAM approach is modified to incorporate the priority of an intruder. The proposed P-DREAM approach assigns the defenders to the prioritized intruders as the first task. A convex territory protection problem is simulated to illustrate the P-DREAM approach. It involves the computation of static parameters and solving the prioritized task assignments with dynamic resource allocation. Monte-Carlo results were conducted to verify the performance of P-DREAM, and the results clearly show that the P-DREAM approach can protect the territory with consistent performance against highly manoeuvring intruders.

In recent years, Game AI research has made important breakthroughs using Reinforcement Learning (RL). Despite this, RL for modern tabletop games has gained little to no attention, even when they offer a range of unique challenges compared to video games. To bridge this gap, we introduce PyTAG, a Python API for interacting with the Tabletop Games framework (TAG). TAG contains a growing set of more than 20 modern tabletop games, with a common API for AI agents. We present techniques for training RL agents in these games and introduce baseline results after training Proximal Policy Optimisation algorithms on a subset of games. Finally, we discuss the unique challenges complex modern tabletop games provide, now open to RL research through PyTAG.

This paper considers the problem of distributed multi-agent learning, where the global aim is to minimize a sum of local objective (empirical loss) functions through local optimization and information exchange between neighbouring nodes. We introduce a Newton-type fully distributed optimization algorithm, Network-GIANT, which is based on GIANT, a Federated learning algorithm that relies on a centralized parameter server. The Network-GIANT algorithm is designed via a combination of gradient-tracking and a Newton-type iterative algorithm at each node with consensus based averaging of local gradient and Newton updates. We prove that our algorithm guarantees semi-global and exponential convergence to the exact solution over the network assuming strongly convex and smooth loss functions. We provide empirical evidence of the superior convergence performance of Network-GIANT over other state-of-art distributed learning algorithms such as Network-DANE and Newton-Raphson Consensus.

We study the problem of fairly allocating a set of indivisible goods among agents with {\em bivalued submodular valuations} -- each good provides a marginal gain of either $a$ or $b$ ($a < b$) and goods have decreasing marginal gains. This is a natural generalization of two well-studied valuation classes -- bivalued additive valuations and binary submodular valuations. We present a simple sequential algorithmic framework, based on the recently introduced Yankee Swap mechanism, that can be adapted to compute a variety of solution concepts, including max Nash welfare (MNW), leximin and $p$-mean welfare maximizing allocations when $a$ divides $b$. This result is complemented by an existing result on the computational intractability of MNW and leximin allocations when $a$ does not divide $b$. We show that MNW and leximin allocations guarantee each agent at least $\frac25$ and $\frac{a}{b+2a}$ of their maximin share, respectively, when $a$ divides $b$. We also show that neither the leximin nor the MNW allocation is guaranteed to be envy free up to one good (EF1). This is surprising since for the simpler classes of bivalued additive valuations and binary submodular valuations, MNW allocations are known to be envy free up to any good (EFX).

This paper studies a general class of stochastic population processes in which agents interact with one another over a network. Agents update their behaviors in a random and decentralized manner according to a policy that depends only on the agent's current state and an estimate of the macroscopic population state, given by a weighted average of the neighboring states. When the number of agents is large and the network is a complete graph (has all-to-all information access), the macroscopic behavior of the population can be well-approximated by a set of deterministic differential equations called a {\it mean-field approximation}. For incomplete networks such characterizations remained previously unclear, i.e., in general whether a suitable mean-field approximation exists for the macroscopic behavior of the population. The paper addresses this gap by establishing a generic theory describing when various mean-field approximations are accurate for \emph{arbitrary} interaction structures. Our results are threefold. Letting $W$ be the matrix describing agent interactions, we first show that a simple mean-field approximation that incorrectly assumes a homogeneous interaction structure is accurate provided $W$ has a large spectral gap. Second, we show that a more complex mean-field approximation which takes into account agent interactions is accurate as long as the Frobenius norm of $W$ is small. Finally, we compare the predictions of the two mean-field approximations through simulations, highlighting cases where using mean-field approximations that assume a homogeneous interaction structure can lead to inaccurate qualitative and quantitative predictions.

In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as a heavy reliance on precise descriptions for decision-making, and the lack of a systematic approach to leverage try-and-fail procedures akin to traditional Reinforcement Learning (RL). REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance. This approach has the advantage of enabling the utilization of offline behaviors from logs and allowing seamless integration with existing foundation models while it does not require any model fine-tuning. Through comparative analysis with existing methods such as Chain-of-Thoughts(CoT) and Reasoning viA Planning(RAP), REX-based methods demonstrate comparable performance and, in certain cases, even surpass the results achieved by these existing techniques. Notably, REX-based methods exhibit remarkable reductions in execution time, enhancing their practical applicability across a diverse set of scenarios.

We introduce Biomaker CA: a Biome Maker project using Cellular Automata (CA). In Biomaker CA, morphogenesis is a first class citizen and small seeds need to grow into plant-like organisms to survive in a nutrient starved environment and eventually reproduce with variation so that a biome survives for long timelines. We simulate complex biomes by means of CA rules in 2D grids and parallelize all of its computation on GPUs through the Python JAX framework. We show how this project allows for several different kinds of environments and laws of 'physics', alongside different model architectures and mutation strategies. We further analyze some configurations to show how plant agents can grow, survive, reproduce, and evolve, forming stable and unstable biomes. We then demonstrate how one can meta-evolve models to survive in a harsh environment either through end-to-end meta-evolution or by a more surgical and efficient approach, called Petri dish meta-evolution. Finally, we show how to perform interactive evolution, where the user decides how to evolve a plant model interactively and then deploys it in a larger environment. We open source Biomaker CA at: https://tinyurl.com/2x8yu34s .

Traditionally, the satisfaction relation in modal logic is defined as a relation w φ between a possible world w and a formula φ. In such a setting, formula φ expresses a property of possible worlds. For example, statement w "There are black holes" expresses the fact that world w has a property of containing black holes. It is also possible to consider logical systems that capture properties of agents rather than of possible worlds. In such systems, satisfaction relation a φ is a relation between an agent a and a formula φ.

When applied to autonomous mobility applications, RL can be used to derive optimal control In the fast-paced world of technological advancements, strategies for maintaining safety, efficiency, and robustness in autonomous mobility has emerged as a transformative innovation, various traffic situations. Furthermore, in order to control the dramatically reshaping numerous aspects of human life, platoon, the use of single-agent RL is not suitable because such as transportation, logistics, and surveillance [1]. These all agents will identically operate when they are located in a complex systems depend on advanced algorithms, sensors, and same space and time with same action-reward settings. Therefore, communication networks to carry out their tasks smoothly for realizing the cooperation and coordination among and proficiently with their own objectives [2]. One crucial multiple agents, multi-agent RL (MARL) algorithms should element that supports the successful functioning of these be utilized [4]-[6]. Among various MARL algorithms, this systems, particularly when operating as a coordinated group, paper considers communication network (CommNet) which is the efficient sharing of information among multiple mobility is widely and actively used in modern distributed computing platforms.

Many real-world games suffer from information asymmetry: one player is only aware of their own payoffs while the other player has the full game information. Examples include the critical domain of security games and adversarial multi-agent reinforcement learning. Information asymmetry renders traditional solution concepts such as Strong Stackelberg Equilibrium (SSE) and Robust-Optimization Equilibrium (ROE) inoperative. We propose a novel solution concept called VISER (Victim Is Secure, Exploiter best-Responds). VISER enables an external observer to predict the outcome of such games. In particular, for security applications, VISER allows the victim to better defend itself while characterizing the most damaging attacks available to the attacker. We show that each player's VISER strategy can be computed independently in polynomial time using linear programming (LP). We also extend VISER to its Markov-perfect counterpart for Markov games, which can be solved efficiently using a series of LPs.