Primal-dual methods have a natural application in Safe Reinforcement Learning (SRL), posed as a constrained policy optimization problem. In practice however, applying primal-dual methods to SRL is challenging, due to the inter-dependency of the learning rate (LR) and Lagrangian multipliers (dual variables) each time an embedded unconstrained RL problem is solved. In this paper, we propose, analyze and evaluate adaptive primal-dual (APD) methods for SRL, where two adaptive LRs are adjusted to the Lagrangian multipliers so as to optimize the policy in each iteration. We theoretically establish the convergence, optimality and feasibility of the APD algorithm. Finally, we conduct numerical evaluation of the practical APD algorithm with four well-known environments in Bullet-Safey-Gym employing two state-of-the-art SRL algorithms: PPO-Lagrangian and DDPG-Lagrangian. All experiments show that the practical APD algorithm outperforms (or achieves comparable performance) and attains more stable training than the constant LR cases. Additionally, we substantiate the robustness of selecting the two adaptive LRs by empirical evidence.

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification models, leaving the landscape of unlearning for generative models relatively unexplored. This paper serves as a bridge, addressing the gap by providing a unifying framework of machine unlearning for image-to-image generative models. Within this framework, we propose a computationally-efficient algorithm, underpinned by rigorous theoretical analysis, that demonstrates negligible performance degradation on the retain samples, while effectively removing the information from the forget samples. Empirical studies on two large-scale datasets, ImageNet-1K and Places-365, further show that our algorithm does not rely on the availability of the retain samples, which further complies with data retention policy. To our best knowledge, this work is the first that represents systemic, theoretical, empirical explorations of machine unlearning specifically tailored for image-to-image generative models. Our code is available at https://github.com/jpmorganchase/l2l-generator-unlearning.

Modern Reinforcement Learning (RL) algorithms are able to outperform humans in a wide variety of tasks. Multi-agent reinforcement learning (MARL) settings present additional challenges, and successful cooperation in mixed-motive groups of agents depends on a delicate balancing act between individual and group objectives. Social conventions and norms, often inspired by human institutions, are used as tools for striking this balance. In this paper, we examine a fundamental, well-studied social convention that underlies cooperation in both animal and human societies: dominance hierarchies. We adapt the ethological theory of dominance hierarchies to artificial agents, borrowing the established terminology and definitions with as few amendments as possible. We demonstrate that populations of RL agents, operating without explicit programming or intrinsic rewards, can invent, learn, enforce, and transmit a dominance hierarchy to new populations. The dominance hierarchies that emerge have a similar structure to those studied in chickens, mice, fish, and other species.

Emergence and causality are two fundamental concepts for understanding complex systems. They are interconnected. On one hand, emergence refers to the phenomenon where macroscopic properties cannot be solely attributed to the cause of individual properties. On the other hand, causality can exhibit emergence, meaning that new causal laws may arise as we increase the level of abstraction. Causal emergence theory aims to bridge these two concepts and even employs measures of causality to quantify emergence. This paper provides a comprehensive review of recent advancements in quantitative theories and applications of causal emergence. Two key problems are addressed: quantifying causal emergence and identifying it in data. Addressing the latter requires the use of machine learning techniques, thus establishing a connection between causal emergence and artificial intelligence. We highlighted that the architectures used for identifying causal emergence are shared by causal representation learning, causal model abstraction, and world model-based reinforcement learning. Consequently, progress in any of these areas can benefit the others. Potential applications and future perspectives are also discussed in the final section of the review.

Creating and evaluating games manually is an arduous and laborious task. Procedural content generation can aid by creating game artifacts, but usually not an entire game. Evolutionary game design, which combines evolutionary algorithms with automated playtesting, has been used to create novel board games with simple equipment; however, the original approach does not include complex tabletop games with dice, cards, and maps. This work proposes an extension of the approach for tabletop games, evaluating the process by generating variants of Risk, a military strategy game where players must conquer map territories to win. We achieved this using a genetic algorithm to evolve the chosen parameters, as well as a rules-based agent to test the games and a variety of quality criteria to evaluate the new variations generated. Our results show the creation of new variations of the original game with smaller maps, resulting in shorter matches. Also, the variants produce more balanced matches, maintaining the usual drama. We also identified limitations in the process, where, in many cases, where the objective function was correctly pursued, but the generated games were nearly trivial. This work paves the way towards promising research regarding the use of evolutionary game design beyond classic board games.

Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information. In this paper, we systematically assess the working memory capacity of ChatGPT, a large language model developed by OpenAI, by examining its performance in verbal and spatial n-back tasks under various conditions. Our experiments reveal that ChatGPT has a working memory capacity limit strikingly similar to that of humans. Furthermore, we investigate the impact of different instruction strategies on ChatGPT's performance and observe that the fundamental patterns of a capacity limit persist. From our empirical findings, we propose that n-back tasks may serve as tools for benchmarking the working memory capacity of large language models and hold potential for informing future efforts aimed at enhancing AI working memory.

Last week, on the eve of the New Hampshire primary, some of the state's voters received a robocall purporting to be from President Joe Biden. Unlike the other such prerecorded calls reminding people to vote, this one had a different ask: Don't bother coming out to the polls, the voice instructed. Better to "save your vote for the November election." The message was strange, even nonsensical, but the voice on the line sure did sound like the president's. And caller ID showed that the call came from a former chair of the New Hampshire Democratic Party, according to the Associated Press.

Sensemaking is a constant and ongoing process by which people associate meaning to experiences. It can be an individual process, known as abduction, or a group process by which people give meaning to collective experiences. The sensemaking of a group is influenced by the abduction process of each person about the experience. Every collaborative process needs some level of sensemaking to show results. For a knowledge intensive process, sensemaking is central and related to most of its tasks. We present findings from a fieldwork executed in knowledge intensive process from the Oil and Gas industry. Our findings indicated that different types of knowledge can be combined to compose the result of a sensemaking process (e.g. decision, the need for more discussion, etc.). This paper presents an initial set of knowledge types that can be combined to compose the result of the sensemaking of a collaborative decision making process. We also discuss ideas for using systems powered by Artificial Intelligence to support sensemaking processes.

The intention of this article is to propose the use of artificial intelligence to detect through analysis by UFO ontology the emergence of verbal and physical aggression related to psychosocial deficiencies and their provoking agents, in an attempt to prevent catastrophic consequences within school environments.

Providing explanations within the recommendation system would boost user satisfaction and foster trust, especially by elaborating on the reasons for selecting recommended items tailored to the user. The predominant approach in this domain revolves around generating text-based explanations, with a notable emphasis on applying large language models (LLMs). However, refining LLMs for explainable recommendations proves impractical due to time constraints and computing resource limitations. As an alternative, the current approach involves training the prompt rather than the LLM. In this study, we developed a model that utilizes the ID vectors of user and item inputs as prompts for GPT-2. We employed a joint training mechanism within a multi-task learning framework to optimize both the recommendation task and explanation task. This strategy enables a more effective exploration of users' interests, improving recommendation effectiveness and user satisfaction. Through the experiments, our method achieving 1.59 DIV, 0.57 USR and 0.41 FCR on the Yelp, TripAdvisor and Amazon dataset respectively, demonstrates superior performance over four SOTA methods in terms of explainability evaluation metric. In addition, we identified that the proposed model is able to ensure stable textual quality on the three public datasets.