This paper introduces a cooperative and decentralized collision avoidance algorithm (CoDe) for small-scale UAV swarms consisting of up to three UAVs. CoDe improves energy efficiency of UAVs by achieving effective cooperation among UAVs. Moreover, CoDe is specifically tailored for UAV's operations by addressing the challenges faced by existing schemes, such as ineffectiveness in selecting actions from continuous action spaces and high computational complexity. CoDe is based on Multi-Agent Reinforcement Learning (MARL), and finds cooperative policies by incorporating a novel credit assignment scheme. The novel credit assignment scheme estimates the contribution of an individual by subtracting a baseline from the joint action value for the swarm. The credit assignment scheme in CoDe outperforms other benchmarks as the baseline takes into account not only the importance of a UAV's action but also the interrelation between UAVs. Furthermore, extensive experiments are conducted against existing MARL-based and conventional heuristic-based algorithms to demonstrate the advantages of the proposed algorithm.

Existing asynchronous MARL methods based on MacDec-POMDP typically construct training trajectory buffers by simply sampling limited and biased data at the endpoints of macro-actions, and directly apply conventional MARL methods on the buffers. As a result, these methods lead to an incomplete and inaccurate representation of the macro-action execution process, along with unsuitable credit assignments. To solve these problems, the T emporal Macro-action Value F actorization (ToMacVF) is proposed to achieve fine-grained temporal credit assignment for macro-action contributions. A centralized training buffer, called Macro-action S egmented Joint Experience R eplay Trajectory (Mac-SJERT), is designed to incorporate with ToMacVF to collect accurate and complete macro-action execution information, supporting a more comprehensive and precise representation of the macro-action process. To ensure principled and fine-grained asynchronous value factorization, the consistency requirement between joint and individual macro-action selection called Tempo ral Mac ro-action based IGM (To-Mac-IGM) is formalized, proving that it generalizes the synchronous cases. Based on To-Mac-IGM, a modularized ToMacVF architecture, which satisfies CTDE principle, is designed to conveniently integrate previous value factorization methods. Next, the ToMacVF algorithm is devised as an implementation of the ToMacVF architecture. Experimental results demonstrate that, compared to asynchronous baselines, our ToMacVF algorithm not only achieves optimal performance but also exhibits strong adaptability and robustness across various asynchronous multi-agent experimental scenarios.

In heterogeneous multi-agent reinforcement learning (MARL), achieving monotonic improvement plays a pivotal role in enhancing performance. The HAPPO algorithm proposes a feasible solution by introducing a sequential update scheme, which requires independent learning with No Parameter-sharing (NoPS). However, heterogeneous MARL generally requires Partial Parameter-sharing (ParPS) based on agent grouping to achieve high cooperative performance. Our experiments prove that directly combining ParPS with the sequential update scheme leads to the policy updating baseline drift problem, thereby failing to achieve improvement. To solve the conflict between monotonic improvement and ParPS, we propose the Optimal Marginal Deterministic Policy Gradient (OMDPG) algorithm. First, we replace the sequentially computed $Q_ψ^s(s,a_{1:i})$ with the Optimal Marginal Q (OMQ) function $ϕ_ψ^*(s,a_{1:i})$ derived from Q-functions. This maintains MAAD's monotonic improvement while eliminating the conflict through optimal joint action sequences instead of sequential policy ratio calculations. Second, we introduce the Generalized Q Critic (GQC) as the critic function, employing pessimistic uncertainty-constrained loss to optimize different Q-value estimations. This provides the required Q-values for OMQ computation and stable baselines for actor updates. Finally, we implement a Centralized Critic Grouped Actor (CCGA) architecture that simultaneously achieves ParPS in local policy networks and accurate global Q-function computation. Experimental results in SMAC and MAMuJoCo environments demonstrate that OMDPG outperforms various state-of-the-art MARL baselines.

Social learning is a powerful mechanism through which agents learn about the world from others. However, humans don't always choose to observe others, since social learning can carry time and cognitive resource costs. How do people balance social and non-social learning? In this paper, we propose a rational mentalizing model of the decision to engage in social learning. This model estimates the utility of social learning by reasoning about the other agent's goal and the informativity of their future actions. It then weighs the utility of social learning against the utility of self-exploration (non-social learning). Using a multi-player treasure hunt game, we show that our model can quantitatively capture human trade-offs between social and non-social learning. Furthermore, our results indicate that these two components allow agents to flexibly apply social learning to achieve their goals more efficiently.

We consider a multi-retailer supply chain where each retailer can dynamically choose when to share information (e.g., local inventory levels or demand observations) with other retailers, incurring a communication cost for each sharing event. This flexible information exchange mechanism contrasts with fixed protocols such as always sharing or never sharing. We formulate a joint optimization of inventory control and communication strategies, aiming to balance the trade-off between communication overhead and operational performance (service levels, holding, and stockout costs). We adopt a common information framework and derive a centralized Partially Observable Markov Decision Process (POMDP) model for a supply chain coordinator. Solving this coordinator's POMDP via dynamic programming characterizes the structure of optimal policies, determining when retailers should communicate and how they should adjust orders based on available information. We show that, in this setting, retailers can often act optimally by sharing only limited summaries of their private data, reducing communication frequency without compromising performance. We also incorporate practical constraints on communication frequency and propose an approximate point-based POMDP solution method (PBVI/SARSOP) to address computational complexity. Numerical experiments on multi-retailer inventory scenarios demonstrate that our approach significantly improves the cost-service trade-off compared to static information sharing policies, effectively optimizing the schedule of information exchange for cooperative inventory control.

What drives an agent to explore the world while also maintaining control over the environment? From a child at play to scientists in the lab, intelligent agents must balance curiosity (the drive to seek knowledge) with competence (the drive to master and control the environment). Bridging cognitive theories of intrinsic motivation with reinforcement learning, we ask how evolving internal representations mediate the trade-off between curiosity (novelty or information gain) and competence (empowerment). We compare two model-based agents using handcrafted state abstractions (Tabular) or learning an internal world model (Dreamer). The Tabular agent shows curiosity and competence guide exploration in distinct patterns, while prioritizing both improves exploration. The Dreamer agent reveals a two-way interaction between exploration and representation learning, mirroring the developmental co-evolution of curiosity and competence.

In most real-world applications of artificial intelligence, the distributions of the data and the goals of the learners tend to change over time. The Probably Approximately Correct (PAC) learning framework, which underpins most machine learning algorithms, fails to account for dynamic data distributions and evolving objectives, often resulting in suboptimal performance. Prospective learning is a recently introduced mathematical framework that overcomes some of these limitations. We build on this framework to present preliminary results that improve the algorithm and numerical results, and extend prospective learning to sequential decision-making scenarios, specifically foraging. Code is available at: https://github.com/neurodata/prolearn2.

Multi-Agent Search and Rescue (MASAR) plays a vital role in disaster response, exploration, and reconnaissance. However, dynamic and unknown environments pose significant challenges due to target unpredictability and environmental uncertainty. To tackle these issues, we propose PILOC, a framework that operates without global prior knowledge, leveraging local perception and communication. It introduces a pheromone inverse guidance mechanism to enable efficient coordination and dynamic target localization. PILOC promotes decentralized cooperation through local communication, significantly reducing reliance on global channels. Unlike conventional heuristics, the pheromone mechanism is embedded into the observation space of Deep Reinforcement Learning (DRL), supporting indirect agent coordination based on environmental cues. We further integrate this strategy into a DRL-based multi-agent architecture and conduct extensive experiments. Results show that combining local communication with pheromone-based guidance significantly boosts search efficiency, adaptability, and system robustness. Compared to existing methods, PILOC performs better under dynamic and communication-constrained scenarios, offering promising directions for future MASAR applications.

We show that mixtures comprised of multicomponent systems typically are much more structurally complex than the sum of their parts; sometimes, infinitely more complex. We contrast this with the more familiar notion of statistical mixtures, demonstrating how statistical mixtures miss key aspects of emergent hierarchical organization. This leads us to identify a new kind of structural complexity inherent in multicomponent systems and to draw out broad consequences for system ergodicity.

Efficient exploration is a well known problem in deep reinforcement learning and this problem is exacerbated in multi-agent reinforcement learning due the intrinsic complexities of such algorithms. There are several approaches to efficiently explore an environment to learn to solve tasks by multi-agent operating in that environment, of which, the idea of expert exploration is investigated in this work. More specifically, this work investigates the application of large-language models as expert planners for efficient exploration in planning based tasks for multiple agents.