The ability to generalize to previously unseen tasks with little to no supervision is a key challenge in modern machine learning research. It is also a cornerstone of a future "General AI". Any artificially intelligent agent deployed in a real world application, must adapt on the fly to unknown environments. Researchers often rely on reinforcement and imitation learning to provide online adaptation to new tasks, through trial and error learning. However, this can be challenging for complex tasks which require many timesteps or large numbers of subtasks to complete. These "long horizon" tasks suffer from sample inefficiency and can require extremely long training times before the agent can learn to perform the necessary longterm planning. In this work, we introduce CASE which attempts to address these issues by training an Imitation Learning agent using adaptive "near future" subgoals. These subgoals are recalculated at each step using compositional arithmetic in a learned latent representation space. In addition to improving learning efficiency for standard long-term tasks, this approach also makes it possible to perform one-shot generalization to previously unseen tasks, given only a single reference trajectory for the task in a different environment. Our experiments show that the proposed approach consistently outperforms the previous state-of-the-art compositional Imitation Learning approach by 30%.

In many self-organising systems the ability to extract necessary resources from the external environment is essential to the system's growth and survival. Examples include the extraction of sunlight and nutrients in organic plants, of monetary income in business organisations and of mobile robots in swarm intelligence actions. When operating within competitive, ever-changing environments, such systems must distribute their internal assets wisely so as to improve and adapt their ability to extract available resources. As the system size increases, the asset-distribution process often gets organised around a multi-scale control topology. This topology may be static (fixed) or dynamic (enabling growth and structural adaptation) depending on the system's internal constraints and adaptive mechanisms. In this paper, we expand on a plant-inspired asset-distribution model and introduce a more general multi-scale model applicable across a wider range of natural and artificial system domains. We study the impact that the topology of the multi-scale control process has upon the system's ability to self-adapt asset distribution when resource availability changes within the environment. Results show how different topological characteristics and different competition levels between system branches impact overall system profitability, adaptation delays and disturbances when environmental changes occur. These findings provide a basis for system designers to select the most suitable topology and configuration for their particular application and execution environment.

With the continuous growth of the global economy and markets, resource imbalance has risen to be one of the central issues in real logistic scenarios. In marine transportation, this trade imbalance leads to Empty Container Repositioning (ECR) problems. Once the freight has been delivered from an exporting country to an importing one, the laden will turn into empty containers that need to be repositioned to satisfy new goods requests in exporting countries. In such problems, the performance that any cooperative repositioning policy can achieve strictly depends on the routes that vessels will follow (i.e., fleet deployment). Historically, Operation Research (OR) approaches were proposed to jointly optimize the repositioning policy along with the fleet of vessels. However, the stochasticity of future supply and demand of containers, together with black-box and non-linear constraints that are present within the environment, make these approaches unsuitable for these scenarios. In this paper, we introduce a novel framework, Configurable Semi-POMDPs, to model this type of problems. Furthermore, we provide a two-stage learning algorithm, "Configure & Conquer" (CC), that first configures the environment by finding an approximation of the optimal fleet deployment strategy, and then "conquers" it by learning an ECR policy in this tuned environmental setting. We validate our approach in large and real-world instances of the problem. Our experiments highlight that CC avoids the pitfalls of OR methods and that it is successful at optimizing both the ECR policy and the fleet of vessels, leading to superior performance in world trade environments.

This paper proposes networked dynamics to solve resource allocation problems over time-varying multi-agent networks. The state of each agent represents the amount of used resources (or produced utilities) while the total amount of resources is fixed. The idea is to optimally allocate the resources among the group of agents by minimizing the overall cost function subject to fixed sum of resources. Each agents' information is restricted to its own state and cost function and those of its immediate in-neighbors. This is motivated by distributed applications such as mobile edge-computing, economic dispatch over smart grids, and multi-agent coverage control. This work provides a fast convergent solution (in comparison with linear dynamics) while considering relaxed network connectivity with quantized communication links. The proposed dynamics reaches optimal solution over switching (possibly disconnected) undirected networks as far as their union over some bounded non-overlapping time-intervals has a spanning-tree. We prove feasibility of the solution, uniqueness of the optimal state, and convergence to the optimal value under the proposed dynamics, where the analysis is applicable to similar 1st-order allocation dynamics with strongly sign-preserving nonlinearities, such as actuator saturation.

We explore active audio-visual separation for dynamic sound sources, where an embodied agent moves intelligently in a 3D environment to continuously isolate the time-varying audio stream being emitted by an object of interest. The agent hears a mixed stream of multiple audio sources (e.g., multiple people conversing and a band playing music at a noisy party). Given a limited time budget, it needs to extract the target sound accurately at every step using egocentric audio-visual observations. We propose a reinforcement learning agent equipped with a novel transformer memory that learns motion policies to control its camera and microphone to recover the dynamic target audio, using self-attention to make high-quality estimates for current timesteps and also simultaneously improve its past estimates. Using highly realistic acoustic SoundSpaces [14] simulations in real-world scanned Matterport3D [12] environments, we show that our model is able to learn efficient behavior to carry out continuous separation of a dynamic audio target.

Collaborative perception has recently shown great potential to improve perception capabilities over single-agent perception. Existing collaborative perception methods usually consider an ideal communication environment. However, in practice, the communication system inevitably suffers from latency issues, causing potential performance degradation and high risks in safety-critical applications, such as autonomous driving. To mitigate the effect caused by the inevitable latency, from a machine learning perspective, we present the first latency-aware collaborative perception system, which actively adapts asynchronous perceptual features from multiple agents to the same time stamp, promoting the robustness and effectiveness of collaboration. To achieve such a feature-level synchronization, we propose a novel latency compensation module, called SyncNet, which leverages feature-attention symbiotic estimation and time modulation techniques. Experiments results show that the proposed latency aware collaborative perception system with SyncNet can outperforms the state-of-the-art collaborative perception method by 15.6% in the communication latency scenario and keep collaborative perception being superior to single agent perception under severe latency.

While single-agent policy optimization in a fixed environment has attracted a lot of research attention recently in the reinforcement learning community, much less is known theoretically when there are multiple agents playing in a potentially competitive environment. We take steps forward by proposing and analyzing new fictitious play policy optimization algorithms for zero-sum Markov games with structured but unknown transitions. We consider two classes of transition structures: factored independent transition and single-controller transition. For both scenarios, we prove tight $\widetilde{\mathcal{O}}(\sqrt{K})$ regret bounds after $K$ episodes in a two-agent competitive game scenario. The regret of each agent is measured against a potentially adversarial opponent who can choose a single best policy in hindsight after observing the full policy sequence. Our algorithms feature a combination of Upper Confidence Bound (UCB)-type optimism and fictitious play under the scope of simultaneous policy optimization in a non-stationary environment. When both players adopt the proposed algorithms, their overall optimality gap is $\widetilde{\mathcal{O}}(\sqrt{K})$.

We identify effective stochastic differential equations (SDE) for coarse observables of fine-grained particle- or agent-based simulations; these SDE then provide useful coarse surrogate models of the fine scale dynamics. We approximate the drift and diffusivity functions in these effective SDE through neural networks, which can be thought of as effective stochastic ResNets. The loss function is inspired by, and embodies, the structure of established stochastic numerical integrators (here, Euler-Maruyama and Milstein); our approximations can thus benefit from backward error analysis of these underlying numerical schemes. They also lend themselves naturally to "physics-informed" gray-box identification when approximate coarse models, such as mean field equations, are available. Existing numerical integration schemes for Langevin-type equations and for stochastic partial differential equations (SPDE) can also be used for training; we demonstrate this on a stochastically forced oscillator and the stochastic wave equation. Our approach does not require long trajectories, works on scattered snapshot data, and is designed to naturally handle different time steps per snapshot. We consider both the case where the coarse collective observables are known in advance, as well as the case where they must be found in a data-driven manner.

In this paper, we focus on solving a distributed convex aggregative optimization problem in a network, where each agent has its own cost function which depends not only on its own decision variables but also on the aggregated function of all agents' decision variables. The decision variable is constrained within a feasible set. In order to minimize the sum of the cost functions when each agent only knows its local cost function, we propose a distributed Frank-Wolfe algorithm based on gradient tracking for the aggregative optimization problem where each node maintains two estimates, namely an estimate of the sum of agents' decision variable and an estimate of the gradient of global function. The algorithm is projection-free, but only involves solving a linear optimization to get a search direction at each step. We show the convergence of the proposed algorithm for convex and smooth objective functions over a time-varying network. Finally, we demonstrate the convergence and computational efficiency of the proposed algorithm via numerical simulations.

As an emerging technology, Connected Autonomous Vehicles (CAVs) are believed to have the ability to move through intersections in a faster and safer manner, through effective Vehicle-to-Everything (V2X) communication and global observation. Autonomous intersection management is a key path to efficient crossing at intersections, which reduces unnecessary slowdowns and stops through adaptive decision process of each CAV, enabling fuller utilization of the intersection space. Distributed reinforcement learning (DRL) offers a flexible, end-to-end model for AIM, adapting for many intersection scenarios. While DRL is prone to collisions as the actions of multiple sides in the complicated interactions are sampled from a generic policy, restricting the application of DRL in realistic scenario. To address this, we propose a hierarchical RL framework where models at different levels vary in receptive scope, action step length, and feedback period of reward. The upper layer model accelerate CAVs to prevent them from being clashed, while the lower layer model adjust the trends from upper layer model to avoid the change of mobile state causing new conflicts. And the real action of CAV at each step is co-determined by the trends from both levels, forming a real-time balance in the adversarial process. The proposed model is proven effective in the experiment undertaken in a complicated intersection with 4 branches and 4 lanes each branch, and show better performance compared with baselines.