Multi-task reinforcement learning (RL) aims to find a single policy that effectively solves multiple tasks at the same time. This paper presents a constrained formulation for multi-task RL where the goal is to maximize the average performance of the policy across tasks subject to bounds on the performance in each task. We consider solving this problem both in the centralized setting, where information for all tasks is accessible to a single server, and in the decentralized setting, where a network of agents, each given one task and observing local information, cooperate to find the solution of the globally constrained objective using local communication. We first propose a primal-dual algorithm that provably converges to the globally optimal solution of this constrained formulation under exact gradient evaluations. When the gradient is unknown, we further develop a sampled-based actor-critic algorithm that finds the optimal policy using online samples of state, action, and reward. Finally, we study the extension of the algorithm to the linear function approximation setting.

We present a novel agent-based approach to simulating an over-the-counter (OTC) financial market in which trades are intermediated solely by market makers and agent visibility is constrained to a network topology. Dynamics, such as changes in price, result from agent-level interactions that ubiquitously occur via market maker agents acting as liquidity providers. Two additional agents are considered: trend investors use a deep convolutional neural network paired with a deep Q-learning framework to inform trading decisions by analysing price history; and value investors use a static price-target to determine their trade directions and sizes. We demonstrate that our novel inclusion of a network topology with market makers facilitates explorations into various market structures. First, we present the model and an overview of its mechanics. Second, we validate our findings via comparison to the real-world: we demonstrate a fat-tailed distribution of price changes, auto-correlated volatility, a skew negatively correlated to market maker positioning, predictable price-history patterns and more. Finally, we demonstrate that our network-based model can lend insights into the effect of market-structure on price-action. For example, we show that markets with sparsely connected intermediaries can have a critical point of fragmentation, beyond which the market forms distinct clusters and arbitrage becomes rapidly possible between the prices of different market makers. A discussion is provided on future work that would be beneficial.

Compact robotic platforms with powerful compute and actuation capabilities are key enablers for practical, real-world deployments of multi-agent research. This article introduces a tightly integrated hardware, control, and simulation software stack on a fleet of holonomic ground robot platforms designed with this motivation. Our robots, a fleet of customised DJI Robomaster S1 vehicles, offer a balance between small robots that do not possess sufficient compute or actuation capabilities and larger robots that are unsuitable for indoor multi-robot tests. They run a modular ROS2-based optimal estimation and control stack for full onboard autonomy, contain ad-hoc peer-to-peer communication infrastructure, and can zero-shot run multi-agent reinforcement learning (MARL) policies trained in our vectorized multi-agent simulation framework. We present an in-depth review of other platforms currently available, showcase new experimental validation of our system's capabilities, and introduce case studies that highlight the versatility and reliabilty of our system as a testbed for a wide range of research demonstrations. Our system as well as supplementary material is available online.

Developing reusable software for mobile robots is still challenging. Even more so for swarm robots, despite the desired simplicity of the robot controllers. Prototyping and experimenting are difficult due to the multi-robot setting and often require robot-robot communication. Also, the diversity of swarm robot hardware platforms increases the need for hardware-independent software concepts. The main advantages of the commonly used robot software architecture ROS 2 are modularity and platform independence. We propose a new ROS 2 package, ROS2swarm, for applications of swarm robotics that provides a library of ready-to-use swarm behavioral primitives. We show the successful application of our approach on three different platforms, the TurtleBot3 Burger, the TurtleBot3 Waffle Pi, and the Jackal UGV, and with a set of different behavioral primitives, such as aggregation, dispersion, and collective decision-making. The proposed approach is easy to maintain, extendable, and has good potential for simplifying swarm robotics experiments in future applications.

Collective decision-making enables multi-robot systems to act autonomously in real-world environments. Existing collective decision-making mechanisms suffer from the so-called speed versus accuracy trade-off or rely on high complexity, e.g., by including global communication. Recent work has shown that more efficient collective decision-making mechanisms based on artificial neural networks can be generated using methods from evolutionary computation. A major drawback of these decision-making neural networks is their limited interpretability. Analyzing evolved decision-making mechanisms can help us improve the efficiency of hand-coded decision-making mechanisms while maintaining a higher interpretability. In this paper, we analyze evolved collective decision-making mechanisms in detail and hand-code two new decision-making mechanisms based on the insights gained. In benchmark experiments, we show that the newly implemented collective decision-making mechanisms are more efficient than the state-of-the-art collective decision-making mechanisms voter model and majority rule.

Recommender selects and presents top-K items to the user at each online request, and a recommendation session consists of several sequential requests. Formulating a recommendation session as a Markov decision process and solving it by reinforcement learning (RL) framework has attracted increasing attention from both academic and industry communities. In this paper, we propose a RL-based industrial short-video recommender ranking framework, which models and maximizes user watch-time in an environment of user multi-aspect preferences by a collaborative multi-agent formulization. Moreover, our proposed framework adopts a model-based learning approach to alleviate the sample selection bias which is a crucial but intractable problem in industrial recommender system. Extensive offline evaluations and live experiments confirm the effectiveness of our proposed method over alternatives. Our proposed approach has been deployed in our real large-scale short-video sharing platform, successfully serving over hundreds of millions users.

Reaching a consensus on the team plans is vital to human-AI coordination. Although previous studies provide approaches through communications in various ways, it could still be hard to coordinate when the AI has no explainable plan to communicate. To cover this gap, we suggest incorporating external models to assist humans in understanding the intentions of AI agents. In this paper, we propose a two-stage paradigm that first trains a Theory of Mind (ToM) model from collected offline trajectories of the target agent, and utilizes the model in the process of human-AI collaboration by real-timely displaying the future action predictions of the target agent. Such a paradigm leaves the AI agent as a black box and thus is available for improving any agents. To test our paradigm, we further implement a transformer-based predictor as the ToM model and develop an extended online human-AI collaboration platform for experiments. The comprehensive experimental results verify that human-AI teams can achieve better performance with the help of our model. A user assessment attached to the experiment further demonstrates that our paradigm can significantly enhance the situational awareness of humans. Our study presents the potential to augment the ability of humans via external assistance in human-AI collaboration, which may further inspire future research.

Robotic applications across industries demand advanced navigation for safe and smooth movement. Smooth path planning is crucial for mobile robots to ensure stable and efficient navigation, as it minimizes jerky movements and enhances overall performance Achieving this requires smooth collision-free paths. Partial Swarm Optimization (PSO) and Potential Field (PF) are notable path-planning techniques, however, they may struggle to produce smooth paths due to their inherent algorithms, potentially leading to suboptimal robot motion and increased energy consumption. In addition, while PSO efficiently explores solution spaces, it generates long paths and has limited global search. On the contrary, PF methods offer concise paths but struggle with distant targets or obstacles. To address this, we propose Smoothed Partial Swarm Optimization with Improved Potential Field (SPSO-IPF), combining both approaches and it is capable of generating a smooth and safe path. Our research demonstrates SPSO-IPF's superiority, proving its effectiveness in static and dynamic environments compared to a mere PSO or a mere PF approach.

In the real world, the strong episode resetting mechanisms that are needed to train agents in simulation are unavailable. The \textit{resetting} assumption limits the potential of reinforcement learning in the real world, as providing resets to an agent usually requires the creation of additional handcrafted mechanisms or human interventions. Recent work aims to train agents (\textit{forward}) with learned resets by constructing a second (\textit{backward}) agent that returns the forward agent to the initial state. We find that the termination and timing of the transitions between these two agents are crucial for algorithm success. With this in mind, we create a new algorithm, Reset Free RL with Intelligently Switching Controller (RISC) which intelligently switches between the two agents based on the agent's confidence in achieving its current goal. Our new method achieves state-of-the-art performance on several challenging environments for reset-free RL.

This paper studies algorithmic decision-making in the presence of strategic individual behaviors, where an ML model is used to make decisions about human agents and the latter can adapt their behavior strategically to improve their future data. Existing results on strategic learning have largely focused on the linear setting where agents with linear labeling functions best respond to a (noisy) linear decision policy. Instead, this work focuses on general non-linear settings where agents respond to the decision policy with only "local information" of the policy. Moreover, we simultaneously consider the objectives of maximizing decision-maker welfare (model prediction accuracy), social welfare (agent improvement caused by strategic behaviors), and agent welfare (the extent that ML underestimates the agents). We first generalize the agent best response model in previous works to the non-linear setting, then reveal the compatibility of welfare objectives. We show the three welfare can attain the optimum simultaneously only under restrictive conditions which are challenging to achieve in non-linear settings. The theoretical results imply that existing works solely maximizing the welfare of a subset of parties inevitably diminish the welfare of the others. We thus claim the necessity of balancing the welfare of each party in non-linear settings and propose an irreducible optimization algorithm suitable for general strategic learning. Experiments on synthetic and real data validate the proposed algorithm.