The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.

The number of IoT devices is predicted to reach 125 billion by 2023. The growth of IoT devices will intensify the collisions between devices, degrading communication performance. Selecting appropriate transmission parameters, such as channel and spreading factor (SF), can effectively reduce the collisions between long-range (LoRa) devices. However, most of the schemes proposed in the current literature are not easy to implement on an IoT device with limited computational complexity and memory. To solve this issue, we propose a lightweight transmission-parameter selection scheme, i.e., a joint channel and SF selection scheme using reinforcement learning for low-power wide area networking (LoRaWAN). In the proposed scheme, appropriate transmission parameters can be selected by simple four arithmetic operations using only Acknowledge (ACK) information. Additionally, we theoretically analyze the computational complexity and memory requirement of our proposed scheme, which verified that our proposed scheme could select transmission parameters with extremely low computational complexity and memory requirement. Moreover, a large number of experiments were implemented on the LoRa devices in the real world to evaluate the effectiveness of our proposed scheme. The experimental results demonstrate the following main phenomena. (1) Compared to other lightweight transmission-parameter selection schemes, collisions between LoRa devices can be efficiently avoided by our proposed scheme in LoRaWAN irrespective of changes in the available channels. (2) The frame success rate (FSR) can be improved by selecting access channels and using SFs as opposed to only selecting access channels. (3) Since interference exists between adjacent channels, FSR and fairness can be improved by increasing the interval of adjacent available channels.

Task scheduling is a critical problem when one user offloads multiple different tasks to the edge server. When a user has multiple tasks to offload and only one task can be transmitted to server at a time, while server processes tasks according to the transmission order, the problem is NP-hard. However, it is difficult for traditional optimization methods to quickly obtain the optimal solution, while approaches based on reinforcement learning face with the challenge of excessively large action space and slow convergence. In this paper, we propose a Digital Twin (DT)-assisted RL-based task scheduling method in order to improve the performance and convergence of the RL. We use DT to simulate the results of different decisions made by the agent, so that one agent can try multiple actions at a time, or, similarly, multiple agents can interact with environment in parallel in DT. In this way, the exploration efficiency of RL can be significantly improved via DT, and thus RL can converges faster and local optimality is less likely to happen. Particularly, two algorithms are designed to made task scheduling decisions, i.e., DT-assisted asynchronous Q-learning (DTAQL) and DT-assisted exploring Q-learning (DTEQL). Simulation results show that both algorithms significantly improve the convergence speed of Q-learning by increasing the exploration efficiency.

The continuous growth of data production in almost all scientific areas raises new problems in data access and management, especially in a scenario where the end-users, as well as the resources that they can access, are worldwide distributed. This work is focused on the data caching management in a Data Lake infrastructure in the context of the High Energy Physics field. We are proposing an autonomous method, based on Reinforcement Learning techniques, to improve the user experience and to contain the maintenance costs of the infrastructure.

This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statistically intractable even for one-layer neural net bandit with a deterministic reward. For both nonlinear bandit and RL, the paper presents a model-based algorithm, Virtual Ascent with Online Model Learner (ViOlin), which provably converges to a local maximum with sample complexity that only depends on the sequential Rademacher complexity of the model class. Our results imply novel global or local regret bounds on several concrete settings such as linear bandit with finite or sparse model class, and two-layer neural net bandit. A key algorithmic insight is that optimism may lead to over-exploration even for two-layer neural net model class. On the other hand, for convergence to local maxima, it suffices to maximize the virtual return if the model can also reasonably predict the size of the gradient and Hessian of the real return.

Many scenarios in mobility and traffic involve multiple different agents that need to cooperate to find a joint solution. Recent advances in behavioral planning use Reinforcement Learning to find effective and performant behavior strategies. However, as autonomous vehicles and vehicle-to-X communications become more mature, solutions that only utilize single, independent agents leave potential performance gains on the road. Multi-Agent Reinforcement Learning (MARL) is a research field that aims to find optimal solutions for multiple agents that interact with each other. This work aims to give an overview of the field to researchers in autonomous mobility. We first explain MARL and introduce important concepts. Then, we discuss the central paradigms that underlie MARL algorithms, and give an overview of state-of-the-art methods and ideas in each paradigm. With this background, we survey applications of MARL in autonomous mobility scenarios and give an overview of existing scenarios and implementations.

This paper studies Stochastic Shortest Path (SSP) problems in known and unknown environments from the perspective of convex optimisation. It first recalls results in the known parameter case, and develops understanding through different proofs. It then focuses on the unknown parameter case, where it studies extended value iteration (EVI) operators. This includes the existing operators used in Rosenberg et al. [26] and Tarbouriech et al. [31] based on the l-1 norm and supremum norm, as well as defining EVI operators corresponding to other norms and divergences, such as the KL-divergence. This paper shows in general how the EVI operators relate to convex programs, and the form of their dual, where strong duality is exhibited. This paper then focuses on whether the bounds from finite horizon research of Neu and Pike-Burke [21] can be applied to these extended value iteration operators in the SSP setting. It shows that similar bounds to [21] for these operators exist, however they lead to operators that are not in general monotone and have more complex convergence properties. In a special case we observe oscillating behaviour. This paper generates open questions on how research may progress, with several examples that require further examination.

Autonomous driving has the potential to revolutionize mobility and is hence an active area of research. In practice, the behavior of autonomous vehicles must be acceptable, i.e., efficient, safe, and interpretable. While vanilla reinforcement learning (RL) finds performant behavioral strategies, they are often unsafe and uninterpretable. Safety is introduced through Safe RL approaches, but they still mostly remain uninterpretable as the learned behaviour is jointly optimized for safety and performance without modeling them separately. Interpretable machine learning is rarely applied to RL. This paper proposes SafeDQN, which allows to make the behavior of autonomous vehicles safe and interpretable while still being efficient. SafeDQN offers an understandable, semantic trade-off between the expected risk and the utility of actions while being algorithmically transparent. We show that SafeDQN finds interpretable and safe driving policies for a variety of scenarios and demonstrate how state-of-the-art saliency techniques can help to assess both risk and utility.

Deep reinforcement learning (deep RL) has emerged as an effective tool for developing controllers for legged robots. However, vanilla deep RL often requires a tremendous amount of training samples and is not feasible for achieving robust behaviors. Instead, researchers have investigated a novel policy architecture by incorporating human experts' knowledge, such as Policies Modulating Trajectory Generators (PMTG). This architecture builds a recurrent control loop by combining a parametric trajectory generator (TG) and a feedback policy network to achieve more robust behaviors. To take advantage of human experts' knowledge but eliminate time-consuming interactive teaching, researchers have investigated a novel architecture, Policies Modulating Trajectory Generators (PMTG), which builds a recurrent control loop by combining a parametric trajectory generator (TG) and a feedback policy network to achieve more robust behaviors using intuitive prior knowledge. In this work, we propose Policies Modulating Finite State Machine (PM-FSM) by replacing TGs with contact-aware finite state machines (FSM), which offer more flexible control of each leg. Compared with the TGs, FSMs offer high-level management on each leg motion generator and enable a flexible state arrangement, which makes the learned behavior less vulnerable to unseen perturbations or challenging terrains. This invention offers an explicit notion of contact events to the policy to negotiate unexpected perturbations. We demonstrated that the proposed architecture could achieve more robust behaviors in various scenarios, such as challenging terrains or external perturbations, on both simulated and real robots. The supplemental video can be found at: https://youtu.be/78cboMqTkJQ.

Vaccinations against viruses have always been the need of the hour since long past. However, it is hard to efficiently distribute the vaccines (on time) to all the corners of a country, especially during a pandemic. Considering the vastness of the population, diversified communities, and demands of a smart society, it is an important task to optimize the vaccine distribution strategy in any country/state effectively. Although there is a profusion of data (Big Data) from various vaccine administration sites that can be mined to gain valuable insights about mass vaccination drives, very few attempts has been made towards revolutionizing the traditional mass vaccination campaigns to mitigate the socio-economic crises of pandemic afflicted countries. In this paper, we bridge this gap in studies and experimentation. We collect daily vaccination data which is publicly available and carefully analyze it to generate meaning-full insights and predictions. We put forward a novel framework leveraging Supervised Learning and Reinforcement Learning (RL) which we call VacciNet, that is capable of learning to predict the demand of vaccination in a state of a country as well as suggest optimal vaccine allocation in the state for minimum cost of procurement and supply. At the present, our framework is trained and tested with vaccination data of the USA.