We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games.

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts. In this work, we present a scalable attack strategy: intent-hiding adversarial prompting, which conceals malicious intent through the composition of skills. We develop a game-theoretic framework to model the interaction between such attacks and defense systems that apply both prompt and response filtering. Our analysis identifies equilibrium points and reveals structural advantages for the attacker. To counter these threats, we propose and analyze a defense mechanism tailored to intent-hiding attacks. Empirically, we validate the attack's effectiveness on multiple real-world LLMs across a range of malicious behaviors, demonstrating clear advantages over existing adversarial prompting techniques.

In adversarial team games, a team of players sequentially faces a team of adversaries.

The brain can rapidly adapt to new contexts and learn from limited data, a coveted characteristic that artificial intelligence algorithms have struggled to mimic. Inspired by oscillatory rhythms of the mechanical structures of neural cells, we developed a learning paradigm that is based on oscillations in link strengths and associates learning with the coordination of these oscillations. We find that this paradigm yields rapid adaptation and learning in artificial neural networks. Link oscillations can rapidly change coordination, endowing the network with the ability to sense subtle context changes in an unsupervised manner. In other words, the network generates the missing contextual tokens required to perform as a generalist AI architecture capable of predicting dynamics in multiple contexts. Oscillations also allow the network to extrapolate dynamics to never-seen-before contexts. These capabilities make our learning paradigm a powerful starting point for novel models of learning and cognition. Furthermore, learning through link coordination is agnostic to the specifics of the neural network architecture, hence our study opens the door for introducing rapid adaptation and learning capabilities into leading AI models.

In Maurice Merleau-Ponty's phenomenology of perception, analysis of perception accounts for an element of intentionality, and in effect therefore, perception and action cannot be viewed as distinct procedures. In the same line of thinking, Alva No\"{e} considers perception as a thoughtful activity that relies on capacities for action and thought. Here, by looking into psychology as a source of inspiration, we propose a computational model for the action involved in visual perception based on the notion of equilibrium as defined by Jean Piaget. In such a model, Piaget's equilibrium reflects the mind's status, which is used to control the observation process. The proposed model is built around a modified version of convolutional neural networks (CNNs) with enhanced filter performance, where characteristics of filters are adaptively adjusted via a high-level control signal that accounts for the thoughtful activity in perception. While the CNN plays the role of the visual system, the control signal is assumed to be a product of mind.

We consider the problem of two-player zero-sum game. In this setting, there are two agents working against each other. Both the agents observe the same state and the objective of the agents is to compute a strategy profile that maximizes their rewards. However, the reward of the second agent is negative of reward obtained by the first agent. Therefore, the objective of the second agent is to minimize the total reward obtained by the first agent. This problem is formulated as a min-max Markov game in the literature. The solution of this game, which is the max-min reward (of first player), starting from a given state is called the equilibrium value of the state. In this work, we compute the solution of the two-player zero-sum game utilizing the technique of successive relaxation. Successive relaxation has been successfully applied in the literature to compute a faster value iteration algorithm in the context of Markov Decision Processes. We extend the concept of successive relaxation to the two-player zero-sum games. We prove that, under a special structure, this technique computes the optimal solution faster than the techniques in the literature. We then derive a generalized minimax Q-learning algorithm that computes the optimal policy when the model information is not known. Finally, we prove the convergence of the proposed generalized minimax Q-learning algorithm.

Single unit activity in the striatum of awake monkeys shows a marked dependence on the expected reward that a behavior will elicit. We present a computational model of spiny neurons, the principal neurons of the striatum, to assess the hypothesis that direct neuromodulatoryeffects of dopamine through the activation of D1 receptors mediate the reward dependency of spiny neuron activity. Dopamine release results in the amplification of key ion currents, leading to the emergence of bistability, which not only modulates the peak firing rate but also introduces a temporal and state dependence of the model's response, thus improving the detectability oftemporally correlated inputs. 1 Introduction The classic notion of the basal ganglia as being involved in purely motor processing has expanded over the years to include sensory and cognitive functions. A surprising newfinding is that much of this activity shows a motivational component. For instance, striatal activity related to visual stimuli is dependent on the type of reinforcement (primary vs secondary) that a behavior will elicit [1].

Single unit activity in the striatum of awake monkeys shows a marked dependence on the expected reward that a behavior will elicit. We present a computational model of spiny neurons, the principal neurons of the striatum, to assess the hypothesis that direct neuromodulatory effects of dopamine through the activation of D 1 receptors mediate the reward dependency of spiny neuron activity. Dopamine release results in the amplification of key ion currents, leading to the emergence of bistability, which not only modulates the peak firing rate but also introduces a temporal and state dependence of the model's response, thus improving the detectability of temporally correlated inputs. 1 Introduction The classic notion of the basal ganglia as being involved in purely motor processing has expanded over the years to include sensory and cognitive functions. A surprising new finding is that much of this activity shows a motivational component. For instance, striatal activity related to visual stimuli is dependent on the type of reinforcement (primary vs secondary) that a behavior will elicit [1].

Single unit activity in the striatum of awake monkeys shows a marked dependence on the expected reward that a behavior will elicit. We present a computational model of spiny neurons, the principal neurons of the striatum, to assess the hypothesis that direct neuromodulatory effects of dopamine through the activation of D 1 receptors mediate the reward dependency of spiny neuron activity. Dopamine release results in the amplification of key ion currents, leading to the emergence of bistability, which not only modulates the peak firing rate but also introduces a temporal and state dependence of the model's response, thus improving the detectability of temporally correlated inputs. 1 Introduction The classic notion of the basal ganglia as being involved in purely motor processing has expanded over the years to include sensory and cognitive functions. A surprising new finding is that much of this activity shows a motivational component. For instance, striatal activity related to visual stimuli is dependent on the type of reinforcement (primary vs secondary) that a behavior will elicit [1].