A pair of researchers from the University of Montreal today published a pre-print research paper on creating "more intelligent artificial agents" by imitating the human brain. We've heard that one before, but this time's a little different. The big idea here is all about giving artificial intelligence agents more agency. Despite the progress made in social neuroscience and in developmental psychology, only in the last decade, serious efforts have started focusing on the neural mechanisms of social interaction, which were seen as the "dark matter" of social neuroscience. Basically, there's something other than just algorithms and architecture that makes our brains tick.

Information sharing is key in building team cognition and enables coordination and cooperation. High-performing human teams also benefit from acting strategically with hierarchical levels of iterated communication and rationalizability, meaning a human agent can reason about the actions of their teammates in their decision-making. Yet, the majority of prior work in Multi-Agent Reinforcement Learning (MARL) does not support iterated rationalizability and only encourage inter-agent communication, resulting in a suboptimal equilibrium cooperation strategy. In this work, we show that reformulating an agent's policy to be conditional on the policies of its neighboring teammates inherently maximizes Mutual Information (MI) lower-bound when optimizing under Policy Gradient (PG). Building on the idea of decision-making under bounded rationality and cognitive hierarchy theory, we show that our modified PG approach not only maximizes local agent rewards but also implicitly reasons about MI between agents without the need for any explicit ad-hoc regularization terms. Our approach, InfoPG, outperforms baselines in learning emergent collaborative behaviors and sets the state-of-the-art in decentralized cooperative MARL tasks. Our experiments validate the utility of InfoPG by achieving higher sample efficiency and significantly larger cumulative reward in several complex cooperative multi-agent domains.

Psychological curiosity plays a significant role in human intelligence to enhance learning through exploration and information acquisition. In the Artificial Intelligence (AI) community, artificial curiosity provides a natural intrinsic motivation for efficient learning as inspired by human cognitive development; meanwhile, it can bridge the existing gap between AI research and practical application scenarios, such as overfitting, poor generalization, limited training samples, high computational cost, etc. As a result, curiosity-driven learning (CDL) has become increasingly popular, where agents are self-motivated to learn novel knowledge. In this paper, we first present a comprehensive review on the psychological study of curiosity and summarize a unified framework for quantifying curiosity as well as its arousal mechanism. Based on the psychological principle, we further survey the literature of existing CDL methods in the fields of Reinforcement Learning, Recommendation, and Classification, where both advantages and disadvantages as well as future work are discussed. As a result, this work provides fruitful insights for future CDL research and yield possible directions for further improvement.

Covering option discovery has been developed to improve the exploration of reinforcement learning in single-agent scenarios with sparse reward signals, through connecting the most distant states in the embedding space provided by the Fiedler vector of the state transition graph. However, these option discovery methods cannot be directly extended to multi-agent scenarios, since the joint state space grows exponentially with the number of agents in the system. Thus, existing researches on adopting options in multi-agent scenarios still rely on single-agent option discovery and fail to directly discover the joint options that can improve the connectivity of the joint state space of agents. In this paper, we show that it is indeed possible to directly compute multi-agent options with collaborative exploratory behaviors among the agents, while still enjoying the ease of decomposition. Our key idea is to approximate the joint state space as a Kronecker graph -- the Kronecker product of individual agents' state transition graphs, based on which we can directly estimate the Fiedler vector of the joint state space using the Laplacian spectrum of individual agents' transition graphs. This decomposition enables us to efficiently construct multi-agent joint options by encouraging agents to connect the sub-goal joint states which are corresponding to the minimum or maximum values of the estimated joint Fiedler vector. The evaluation based on multi-agent collaborative tasks shows that the proposed algorithm can successfully identify multi-agent options, and significantly outperforms prior works using single-agent options or no options, in terms of both faster exploration and higher cumulative rewards.

Autonomous driving has been at the forefront of public interest, and a pivotal debate to widespread concerns is safety in the transportation system. Deep reinforcement learning (DRL) has been applied to autonomous driving to provide solutions for obstacle avoidance. However, in a road traffic junction scenario, the vehicle typically receives partial observations from the transportation environment, while DRL needs to rely on long-term rewards to train a reliable model by maximising the cumulative rewards, which may take the risk when exploring new actions and returning either a positive reward or a penalty in the case of collisions. Although safety concerns are usually considered in the design of a reward function, they are not fully considered as the critical metric to directly evaluate the effectiveness of DRL algorithms in autonomous driving. In this study, we evaluated the safety performance of three baseline DRL models (DQN, A2C, and PPO) and proposed a self-awareness module from an attention mechanism for DRL to improve the safety evaluation for an anomalous vehicle in a complex road traffic junction environment, such as intersection and roundabout scenarios, based on four metrics: collision rate, success rate, freezing rate, and total reward. Our two experimental results in the training and testing phases revealed the baseline DRL with poor safety performance, while our proposed self-awareness attention-DQN can significantly improve the safety performance in intersection and roundabout scenarios.

Assessing the effects of a policy based on observational data from a different policy is a common problem across several high-stake decision-making domains, and several off-policy evaluation (OPE) techniques have been proposed. However, these methods largely formulate OPE as a problem disassociated from the process used to generate the data (i.e. structural assumptions in the form of a causal graph). We argue that explicitly highlighting this association has important implications on our understanding of the fundamental limits of OPE. First, this implies that current formulation of OPE corresponds to a narrow set of tasks, i.e. a specific causal estimand which is focused on prospective evaluation of policies over populations or sub-populations. Second, we demonstrate how this association motivates natural desiderata to consider a general set of causal estimands, particularly extending the role of OPE for counterfactual off-policy evaluation at the level of individuals of the population. A precise description of the causal estimand highlights which OPE estimands are identifiable from observational data under the stated generative assumptions. For those OPE estimands that are not identifiable, the causal perspective further highlights where more experimental data is necessary, and highlights situations where human expertise can aid identification and estimation. Furthermore, many formalisms of OPE overlook the role of uncertainty entirely in the estimation process.We demonstrate how specifically characterising the causal estimand highlights the different sources of uncertainty and when human expertise can naturally manage this uncertainty. We discuss each of these aspects as actionable desiderata for future OPE research at scale and in-line with practical utility.

While artificial intelligence (AI) agents have become increasingly skilled at communicating with humans, they still struggle with several aspects of language, including complex semantics. The term semantics refers to the area of linguistics that relates to the meaning associated with specific words or logical connections between different concepts. A few years ago, researchers at Allen Institute for AI developed a game called Iconary, which is designed to improve the ability of AI techniques to communicate and make connections between different objects. In a recent paper pre-published on arXiv and presented at last year's ENMLP conference, the researchers introduced a more advanced version of the game and trained machine learning algorithms to play against each other or with humans. "Our paper is based on a project at AI2 aimed at training models to play Iconary, a Pictionary-based game we created, where a player has to guess what another player is drawing," Christopher Clark, one of the researchers who carried out the study, told TechXplore.

One of the most remarkable things about the human moral mind is its flexibility. We can make moral judgments about cases we have never seen before. We can decide that pre-established rules should be broken. We can invent novel rules on the fly. Capturing this flexibility is one of the central challenges in developing AI systems that can interpret and produce human-like moral judgment. This paper details the results of a study of real-world decision makers who judge whether it is acceptable to break a well-established norm: ``no cutting in line.'' We gather data on how human participants judge the acceptability of line-cutting in a range of scenarios. Then, in order to effectively embed these reasoning capabilities into a machine, we propose a method for modeling them using a preference-based structure, which captures a novel modification to standard ``dual process'' theories of moral judgment.

Traditionally, the performance of multi-agent deep reinforcement learning algorithms are demonstrated and validated in gaming environments where we often have a fixed number of agents. In many industrial applications, the number of available agents can change at any given day and even when the number of agents is known ahead of time, it is common for an agent to break during the operation and become unavailable for a period of time. In this paper, we propose a new deep reinforcement learning algorithm for multi-agent collaborative tasks with a variable number of agents. We demonstrate the application of our algorithm using a fleet management simulator developed by Hitachi to generate realistic scenarios in a production site.

Multi-agent reinforcement learning (MARL) is a powerful framework for studying emergent behavior in complex agent-based simulations. However, RL agents are often assumed to be rational and behave optimally, which does not fully reflect human behavior. Here, we study more human-like RL agents which incorporate an established model of human-irrationality, the Rational Inattention (RI) model. RI models the cost of cognitive information processing using mutual information. Our RIRL framework generalizes and is more flexible than prior work by allowing for multi-timestep dynamics and information channels with heterogeneous processing costs. We evaluate RIRL in Principal-Agent (specifically manager-employee relations) problem settings of varying complexity where RI models information asymmetry (e.g. it may be costly for the manager to observe certain information about the employees). We show that using RIRL yields a rich spectrum of new equilibrium behaviors that differ from those found under rational assumptions. For instance, some forms of a Principal's inattention can increase Agent welfare due to increased compensation, while other forms of inattention can decrease Agent welfare by encouraging extra work effort. Additionally, new strategies emerge compared to those under rationality assumptions, e.g., Agents are incentivized to increase work effort. These results suggest RIRL is a powerful tool towards building AI agents that can mimic real human behavior.