Modelling human cognition can provide key insights into behavioral dynamics under changing conditions. This enables synthetic data generation and guides adaptive interventions for cognitive regulation. Challenges arise when environments are highly dynamic, obscuring stimulus-behavior relationships. We propose a cognitive agent integrating drift-diffusion with deep reinforcement learning to simulate granular stress effects on logical reasoning process. Leveraging a large dataset of 21,157 logical responses, we investigate performance impacts of dynamic stress. This prior knowledge informed model design and evaluation. Quantitatively, the framework improves cognition modelling by capturing both subject-specific and stimuli-specific behavioural differences. Qualitatively, it captures general trends in human logical reasoning under stress. Our approach is extensible to examining diverse environmental influences on cognition and behavior. Overall, this work demonstrates a powerful, data-driven methodology to simulate and understand the vagaries of human logical reasoning process in dynamic contexts.

Adopting reasonable strategies is challenging but crucial for an intelligent agent with limited resources working in hazardous, unstructured, and dynamic environments to improve the system's utility, decrease the overall cost, and increase mission success probability. This paper proposes a novel directed acyclic strategy graph decomposition approach based on Bayesian chaining to separate an intricate policy into several simple sub-policies and organize their relationships as Bayesian strategy networks (BSN). We integrate this approach into the state-of-the-art DRL method -- soft actor-critic (SAC), and build the corresponding Bayesian soft actor-critic (BSAC) model by organizing several sub-policies as a joint policy. We compare our method against the state-of-the-art deep reinforcement learning algorithms on the standard continuous control benchmarks in the OpenAI Gym environment. The results demonstrate that the promising potential of the BSAC method significantly improves training efficiency.

Contemporary artificial intelligence systems exhibit rapidly growing abilities accompanied by the growth of required resources, expansive datasets and corresponding investments into computing infrastructure. Although earlier successes predominantly focus on constrained settings, recent strides in fundamental research and applications aspire to create increasingly general systems. This evolving landscape presents a dual panorama of opportunities and challenges in refining the generalisation and transfer of knowledge - the extraction from existing sources and adaptation as a comprehensive foundation for tackling new problems. Within the domain of reinforcement learning (RL), the representation of knowledge manifests through various modalities, including dynamics and reward models, value functions, policies, and the original data. This taxonomy systematically targets these modalities and frames its discussion based on their inherent properties and alignment with different objectives and mechanisms for transfer. Where possible, we aim to provide coarse guidance delineating approaches which address requirements such as limiting environment interactions, maximising computational efficiency, and enhancing generalisation across varying axes of change. Finally, we analyse reasons contributing to the prevalence or scarcity of specific forms of transfer, the inherent potential behind pushing these frontiers, and underscore the significance of transitioning from designed to learned transfer.

Reinforcement learning has shown promising results in learning neural network policies for complicated control tasks. However, the lack of formal guarantees about the behavior of such policies remains an impediment to their deployment. We propose a novel method for learning a composition of neural network policies in stochastic environments, along with a formal certificate which guarantees that a specification over the policy's behavior is satisfied with the desired probability. Unlike prior work on verifiable RL, our approach leverages the compositional nature of logical specifications provided in SpectRL, to learn over graphs of probabilistic reach-avoid specifications. The formal guarantees are provided by learning neural network policies together with reach-avoid supermartingales (RASM) for the graph's sub-tasks and then composing them into a global policy. We also derive a tighter lower bound compared to previous work on the probability of reach-avoidance implied by a RASM, which is required to find a compositional policy with an acceptable probabilistic threshold for complex tasks with multiple edge policies. We implement a prototype of our approach and evaluate it on a Stochastic Nine Rooms environment.

Recent advancements in Large Language Models (LLMs) have exhibited notable efficacy in question-answering (QA) tasks across diverse domains. Their prowess in integrating extensive web knowledge has fueled interest in developing LLM-based autonomous agents. While LLMs are efficient in decoding human instructions and deriving solutions by holistically processing historical inputs, transitioning to purpose-driven agents requires a supplementary rational architecture to process multi-source information, establish reasoning chains, and prioritize critical tasks. Addressing this, we introduce \textsc{FinMem}, a novel LLM-based agent framework devised for financial decision-making. It encompasses three core modules: Profiling, to customize the agent's characteristics; Memory, with layered message processing, to aid the agent in assimilating hierarchical financial data; and Decision-making, to convert insights gained from memories into investment decisions. Notably, \textsc{FinMem}'s memory module aligns closely with the cognitive structure of human traders, offering robust interpretability and real-time tuning. Its adjustable cognitive span allows for the retention of critical information beyond human perceptual limits, thereby enhancing trading outcomes. This framework enables the agent to self-evolve its professional knowledge, react agilely to new investment cues, and continuously refine trading decisions in the volatile financial environment. We first compare \textsc{FinMem} with various algorithmic agents on a scalable real-world financial dataset, underscoring its leading trading performance in stocks. We then fine-tuned the agent's perceptual span and character setting to achieve a significantly enhanced trading performance. Collectively, \textsc{FinMem} presents a cutting-edge LLM agent framework for automated trading, boosting cumulative investment returns.

Extensive research has been devoted to the field of multi-agent navigation. Recently, there has been remarkable progress attributed to the emergence of learning-based techniques with substantially elevated intelligence and realism. Nonetheless, prevailing learned models face limitations in terms of scalability and effectiveness, primarily due to their agent-centric nature, i.e., the learned neural policy is individually deployed on each agent. Inspired by the efficiency observed in real-world traffic networks, we present an environment-centric navigation policy. Our method learns a set of traffic rules to coordinate a vast group of unintelligent agents that possess only basic collision-avoidance capabilities. Our method segments the environment into distinct blocks and parameterizes the traffic rule using a Graph Recurrent Neural Network (GRNN) over the block network. Each GRNN node is trained to modulate the velocities of agents as they traverse through. Using either Imitation Learning (IL) or Reinforcement Learning (RL) schemes, we demonstrate the efficacy of our neural traffic rules in resolving agent congestion, closely resembling real-world traffic regulations. Our method handles up to $240$ agents at real-time and generalizes across diverse agent and environment configurations.

The field of Multi-Agent Reinforcement Learning (MARL) is currently facing a reproducibility crisis. While solutions for standardized reporting have been proposed to address the issue, we still lack a benchmarking tool that enables standardization and reproducibility, while leveraging cutting-edge Reinforcement Learning (RL) implementations. In this paper, we introduce BenchMARL, the first MARL training library created to enable standardized benchmarking across different algorithms, models, and environments. BenchMARL uses TorchRL as its backend, granting it high performance and maintained state-of-the-art implementations while addressing the broad community of MARL PyTorch users. Its design enables systematic configuration and reporting, thus allowing users to create and run complex benchmarks from simple one-line inputs.

Due to its decentralised, distributed and scalable nature, swarm robotics has great potential for applications ranging from agriculture to environmental monitoring and logistics. Various swarm control methods and algorithms are currently known, such as virtual leader, vector and potential field, and others. Such methods often show good results in specific conditions and tasks. The variety of tasks solved by the swarm requires the development of a universal control algorithm. In this paper, we propose an evolution of a thermal motion equivalent method (TMEM) inspired by the behavioural similarity of thermodynamic interactions between molecules. Previous research has shown the high efficiency of such a method for terrain monitoring tasks. This work addresses the problem of swarm formation of geometric structures, as required for logistics and formation movement tasks. It is shown that the formation of swarm geometric structures using the TMEM is possible with a special nonlinear interaction function of the agents. A piecewise linear interaction function is proposed that allows the formation of a stable group of agents. The results of the paper are validated by numerical modelling of the swarm dynamics. A linear quadrocopter model is considered as an agent. The fairness of the choice of the interaction function is shown.

Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the goal of being evaluated as truthful). There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games. We introduce a formal definition of deception in structural causal games, grounded in the philosophy literature, and applicable to real-world machine learning systems. Several examples and results illustrate that our formal definition aligns with the philosophical and commonsense meaning of deception. Our main technical result is to provide graphical criteria for deception. We show, experimentally, that these results can be used to mitigate deception in reinforcement learning agents and language models.

This article investigates the practical scenarios of chasing an adversarial evader in an unbounded environment with cluttered obstacles. We propose a Voronoi-based decentralized algorithm for multiple pursuers to encircle and capture the evader by reacting to collisions. An efficient approach is presented for constructing an obstacle-aware evader-centered bounded Voronoi cell (OA-ECBVC), which strictly ensures collision avoidance in various obstacle scenarios when pursuing the evader. The evader can be efficiently enclosed in a convex hull given random initial configurations. Furthermore, to cooperatively capture the evader, each pursuer continually compresses the boundary of its OA-ECBVC to quickly reduce the movement space of the evader while maintaining encirclement. Our OA-ECBVC algorithm is validated in various simulated environments with different dynamic systems of robots. Real-time performance of resisting uncertainties shows the superior reliability of our method for deployment on multiple robot platforms.