LOBs [22] are a fundamental market mechanism, which are used across a significant proportion of financial markets, including all major stock and derivatives exchanges. The benefits of having robust and realistic simulators for these markets are numerous. For example, they would allow the study of markets under different assumptions, and the investigation of AI techniques for training trading strategies. In a LOB market, matched orders result in trades and unmatched orders are stored in the two parts of the LOB, a collection of buy orders called bids (the bid book), and a collection of sell orders called asks (the ask book). Typically, each side of the LOB will contains hundreds of individual orders, and a real market would be updated at micro-second time resolution, driven by a wide range of market participants and facilitated by "high-frequency" market makers [45]. The development of AI-based automated trading strategies for LOB markets has been a growth area in recent years, both within academia and industry, spurred on in part by developments in deep learning and reinforcement learning. Two typical LOB trading problems that have been investigated are market making, where the goal is to provide liquidity to the market by being continually willing to buy and sell an asset (see, e.g., Spooner et al. [50], Jerome et al. [28], Gasperov and Kostanjcar 1

In this paper, we address the problem of autonomous search and vessel detection in an unknown GNSS-denied maritime environment with fixed-wing UAVs. The main challenge in such environments with limited localization, communication range, and the total number of UAVs and sensors is to implement an appropriate search strategy so that a target vessel can be detected as soon as possible. Thus we present informed and non-informed methods used to search the environment. The informed method relies on an obtained probabilistic map, while the non-informed method navigates the UAVs along predefined paths computed with respect to the environment. The vessel detection method is trained on synthetic data collected in the simulator with data annotation tools. Comparative experiments in simulation have shown that our combination of sensors, search methods and a vessel detection algorithm leads to a successful search for the target vessel in such challenging environments.

We focus on decentralized stochastic non-convex optimization, where $n$ agents work together to optimize a composite objective function which is a sum of a smooth term and a non-smooth convex term. To solve this problem, we propose two single-time scale algorithms: Prox-DASA and Prox-DASA-GT. These algorithms can find $\epsilon$-stationary points in $\mathcal{O}(n^{-1}\epsilon^{-2})$ iterations using constant batch sizes (i.e., $\mathcal{O}(1)$). Unlike prior work, our algorithms achieve comparable complexity without requiring large batch sizes, more complex per-iteration operations (such as double loops), or stronger assumptions. Our theoretical findings are supported by extensive numerical experiments, which demonstrate the superiority of our algorithms over previous approaches. Our code is available at https://github.com/xuxingc/ProxDASA.

Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it suffers from a critical drawback due to its reliance on learning from a single sample of the joint-action at a given state. As agents explore and update their policies during training, these single samples may poorly represent the actual joint-policy of the system of agents leading to high variance gradient estimates that hinder learning. To address this problem, we propose an enhancement tool that accommodates any actor-critic MARL method. Our framework, Performance Enhancing Reinforcement Learning Apparatus (PERLA), introduces a sampling technique of the agents' joint-policy into the critics while the agents train. This leads to TD updates that closely approximate the true expected value under the current joint-policy rather than estimates from a single sample of the joint-action at a given state. This produces low variance and precise estimates of expected returns, minimising the variance in the critic estimators which typically hinders learning. Moreover, as we demonstrate, by eliminating much of the critic variance from the single sampling of the joint policy, PERLA enables CT-DE methods to scale more efficiently with the number of agents. Theoretically, we prove that PERLA reduces variance in value estimates similar to that of decentralised training while maintaining the benefits of centralised training. Empirically, we demonstrate PERLA's superior performance and ability to reduce estimator variance in a range of benchmarks including Multi-agent Mujoco, and StarCraft II Multi-agent Challenge.

In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most current studies either fail to or artificially incorporate such agent-side initiative. This work presents InSCIt, a dataset for Information-Seeking Conversations with mixed-initiative Interactions. It contains 4.7K user-agent turns from 805 human-human conversations where the agent searches over Wikipedia and either directly answers, asks for clarification, or provides relevant information to address user queries. The data supports two subtasks, evidence passage identification and response generation, as well as a human evaluation protocol to assess model performance. We report results of two systems based on state-of-the-art models of conversational knowledge identification and open-domain question answering. Both systems significantly underperform humans, suggesting ample room for improvement in future studies.

Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories; 2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories.

Autonomous agents acting in real-world environments often need to reason with unknown novelties interfering with their plan execution. Novelty is an unexpected phenomenon that can alter the core characteristics, composition, and dynamics of the environment. Novelty can occur at any time in any sufficiently complex environment without any prior notice or explanation. Previous studies show that novelty has catastrophic impact on agent performance. Intelligent agents reason with an internal model of the world to understand the intricacies of their environment and to successfully execute their plans. The introduction of novelty into the environment usually renders their internal model inaccurate and the generated plans no longer applicable. Novelty is particularly prevalent in the real world where domain-specific and even predicted novelty-specific approaches are used to mitigate the novelty's impact. In this work, we demonstrate that a domain-independent AI agent designed to detect, characterize, and accommodate novelty in smaller-scope physics-based games such as Angry Birds and Cartpole can be adapted to successfully perform and reason with novelty in realistic high-fidelity simulator of the military domain.

Unlike most human-engineered systems, biological systems are emergent from low-level interactions, allowing much broader diversity and superior adaptation to the complex environments. Inspired by the process of morphogenesis in nature, a bottom-up design approach for robot morphology is proposed to treat a robot's body as an emergent response to underlying processes rather than a predefined shape. This paper presents Loopy, a "Swarm-of-One" polymorphic robot testbed that can be viewed simultaneously as a robotic swarm and a single robot. Loopy's shape is determined jointly by self-organization and morphological computing using physically linked homogeneous cells. Experimental results show that Loopy can form symmetric shapes consisting of lobes. Using the the same set of parameters, even small amounts of initial noise can change the number of lobes formed. However, once in a stable configuration, Loopy has an "inertia" to transfiguring in response to dynamic parameters. By making the connections among self-organization, morphological computing, and robot design, this paper lays the foundation for more adaptable robot designs in the future.

The emergent behavior of a distributed system is conditioned by the information available to the local decision-makers. Therefore, one may expect that providing decision-makers with more information will improve system performance; in this work, we find that this is not necessarily the case. In multi-agent maximum coverage problems, we find that even when agents' objectives are aligned with the global welfare, informing agents about the realization of the resource's random values can reduce equilibrium performance by a factor of 1/2. This affirms an important aspect of designing distributed systems: information need be shared carefully. We further this understanding by providing lower and upper bounds on the ratio of system welfare when information is (fully or partially) revealed and when it is not, termed the value-of-informing. We then identify a trade-off that emerges when optimizing the performance of the best-case and worst-case equilibrium.

Transfer learning can be applied in deep reinforcement learning to accelerate the training of a policy in a target task by transferring knowledge from a policy learned in a related source task. This is commonly achieved by copying pretrained weights from the source policy to the target policy prior to training, under the constraint that they use the same model architecture. However, not only does this require a robust representation learned over a wide distribution of states -- often failing to transfer between specialist models trained over single tasks -- but it is largely uninterpretable and provides little indication of what knowledge is transferred. In this work, we propose an alternative approach to transfer learning between tasks based on action advising, in which a teacher trained in a source task actively guides a student's exploration in a target task. Through introspection, the teacher is capable of identifying when advice is beneficial to the student and should be given, and when it is not. Our approach allows knowledge transfer between policies agnostic of the underlying representations, and we empirically show that this leads to improved convergence rates in Gridworld and Atari environments while providing insight into what knowledge is transferred.