Heading towards navigational autonomy in unmanned surface vehicles (USVs) in the maritime sector can fundamentally lead towards safer waters as well as reduced operating costs, while also providing a range of exciting new capabilities for oceanic research, exploration and monitoring. However, achieving such a goal is challenging. USV control systems must, safely and reliably, be able to adhere to the international regulations for preventing collisions at sea (COLREGs) in encounters with other vessels as they navigate to a given waypoint while being affected by realistic weather conditions, either during the day or at night. To deal with the multitude of possible scenarios, it is critical to have a virtual environment that is able to replicate the realistic operating conditions USVs will encounter, before they can be implemented in the real world. Such "digital twins" form the foundations upon which Deep Reinforcement Learning (DRL) and Computer Vision (CV) algorithms can be used to develop and guide USV control systems. In this paper we describe the novel development of a COLREG-compliant DRL-based collision avoidant navigational system with CV-based awareness in a realistic ocean simulation environment. The performance of the trained autonomous Agents resulting from this approach is evaluated in several successful navigations to set waypoints in both open sea and coastal encounters with other vessels. A binary executable version of the simulator with trained agents is available at https://github.com/aavek/Aeolus-Ocean

In this work, the novel Image Transformation Sequence Retrieval (ITSR) task is presented, in which a model must retrieve the sequence of transformations between two given images that act as source and target, respectively. Given certain characteristics of the challenge such as the multiplicity of a correct sequence or the correlation between consecutive steps of the process, we propose a solution to ITSR using a general model-based Reinforcement Learning such as Monte Carlo Tree Search (MCTS), which is combined with a deep neural network. Our experiments provide a benchmark in both synthetic and real domains, where the proposed approach is compared with supervised training. The results report that a model trained with MCTS is able to outperform its supervised counterpart in both the simplest and the most complex cases. Our work draws interesting conclusions about the nature of ITSR and its associated challenges.

Prescriptive process monitoring methods seek to optimize the performance of business processes by triggering interventions at runtime, thereby increasing the probability of positive case outcomes. These interventions are triggered according to an intervention policy. Reinforcement learning has been put forward as an approach to learning intervention policies through trial and error. Existing approaches in this space assume that the number of resources available to perform interventions in a process is unlimited, an unrealistic assumption in practice. This paper argues that, in the presence of resource constraints, a key dilemma in the field of prescriptive process monitoring is to trigger interventions based not only on predictions of their necessity, timeliness, or effect but also on the uncertainty of these predictions and the level of resource utilization. Indeed, committing scarce resources to an intervention when the necessity or effects of this intervention are highly uncertain may intuitively lead to suboptimal intervention effects. Accordingly, the paper proposes a reinforcement learning approach for prescriptive process monitoring that leverages conformal prediction techniques to consider the uncertainty of the predictions upon which an intervention decision is based. An evaluation using real-life datasets demonstrates that explicitly modeling uncertainty using conformal predictions helps reinforcement learning agents converge towards policies with higher net intervention gain

Objective: The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM). However, designing an effective control policy for the AP remains challenging due to the complex physiological processes, delayed insulin response, and inaccurate glucose measurements. While model predictive control (MPC) offers safety and stability through the dynamic model and safety constraints, it lacks individualization and is adversely affected by unannounced meals. Conversely, deep reinforcement learning (DRL) provides personalized and adaptive strategies but faces challenges with distribution shifts and substantial data requirements. Methods: We propose a hybrid control policy for the artificial pancreas (HyCPAP) to address the above challenges. HyCPAP combines an MPC policy with an ensemble DRL policy, leveraging the strengths of both policies while compensating for their respective limitations. To facilitate faster deployment of AP systems in real-world settings, we further incorporate meta-learning techniques into HyCPAP, leveraging previous experience and patient-shared knowledge to enable fast adaptation to new patients with limited available data. Results: We conduct extensive experiments using the FDA-accepted UVA/Padova T1DM simulator across three scenarios. Our approaches achieve the highest percentage of time spent in the desired euglycemic range and the lowest occurrences of hypoglycemia. Conclusion: The results clearly demonstrate the superiority of our methods for closed-loop glucose management in individuals with T1DM. Significance: The study presents novel control policies for AP systems, affirming the great potential of proposed methods for efficient closed-loop glucose control.

The dynamic nature of driving environments and the presence of diverse road users pose significant challenges for decision-making in autonomous driving. Deep reinforcement learning (DRL) has emerged as a popular approach to tackle this problem. However, the application of existing DRL solutions is mainly confined to simulated environments due to safety concerns, impeding their deployment in real-world. To overcome this limitation, this paper introduces a novel neuro-symbolic model-free DRL approach, called DRL with Symbolic Logics (DRLSL) that combines the strengths of DRL (learning from experience) and symbolic first-order logics (knowledge-driven reasoning) to enable safe learning in real-time interactions of autonomous driving within real environments. This innovative approach provides a means to learn autonomous driving policies by actively engaging with the physical environment while ensuring safety. We have implemented the DRLSL framework in autonomous driving using the highD dataset and demonstrated that our method successfully avoids unsafe actions during both the training and testing phases. Furthermore, our results indicate that DRLSL achieves faster convergence during training and exhibits better generalizability to new driving scenarios compared to traditional DRL methods.

Most medical treatment decisions are sequential in nature. Hence, there is substantial hope that reinforcement learning may make it possible to formulate precise data-driven treatment plans. However, a key challenge for most applications in this field is the sparse nature of primarily mortality-based reward functions, leading to decreased stability of offline estimates. In this work, we introduce a deep Q-learning approach able to obtain more reliable critical care policies. This method integrates relevant but noisy intermediate biomarker signals into the reward specification, without compromising the optimization of the main outcome of interest (e.g. patient survival). We achieve this by first pruning the action set based on all available rewards, and second training a final model based on the sparse main reward but with a restricted action set. By disentangling accurate and approximated rewards through action pruning, potential distortions of the main objective are minimized, all while enabling the extraction of valuable information from intermediate signals that can guide the learning process. We evaluate our method in both off-policy and offline settings using simulated environments and real health records of patients in intensive care units. Our empirical results indicate that pruning significantly reduces the size of the action space while staying mostly consistent with the actions taken by physicians, outperforming the current state-of-the-art offline reinforcement learning method conservative Q-learning. Our work is a step towards developing reliable policies by effectively harnessing the wealth of available information in data-intensive critical care environments.

Attention has become a common ingredient in deep learning architectures. It adds a dynamical selection of information on top of the static selection of information supported by weights. In the same way, we can imagine a higher-order informational filter built on top of attention: an Attention Schema (AS), namely, a descriptive and predictive model of attention. In cognitive neuroscience, Attention Schema Theory (AST) supports this idea of distinguishing attention from AS. A strong prediction of this theory is that an agent can use its own AS to also infer the states of other agents' attention and consequently enhance coordination with other agents. As such, multi-agent reinforcement learning would be an ideal setting to experimentally test the validity of AST. We explore different ways in which attention and AS interact with each other. Our preliminary results indicate that agents that implement the AS as a recurrent internal control achieve the best performance. In general, these exploratory experiments suggest that equipping artificial agents with a model of attention can enhance their social intelligence.

Efficient exploration is critical in cooperative deep Multi-Agent Reinforcement Learning (MARL). In this work, we propose an exploration method that effectively encourages cooperative exploration based on the idea of sequential action-computation scheme. The high-level intuition is that to perform optimism-based exploration, agents would explore cooperative strategies if each agent's optimism estimate captures a structured dependency relationship with other agents. Assuming agents compute actions following a sequential order at \textit{each environment timestep}, we provide a perspective to view MARL as tree search iterations by considering agents as nodes at different depths of the search tree. Inspired by the theoretically justified tree search algorithm UCT (Upper Confidence bounds applied to Trees), we develop a method called Conditionally Optimistic Exploration (COE). COE augments each agent's state-action value estimate with an action-conditioned optimistic bonus derived from the visitation count of the global state and joint actions of preceding agents. COE is performed during training and disabled at deployment, making it compatible with any value decomposition method for centralized training with decentralized execution. Experiments across various cooperative MARL benchmarks show that COE outperforms current state-of-the-art exploration methods on hard-exploration tasks.

Learning long-horizon tasks such as navigation has presented difficult challenges for successfully applying reinforcement learning to robotics. From another perspective, under known environments, sampling-based planning can robustly find collision-free paths in environments without learning. In this work, we propose Control Transformer that models return-conditioned sequences from low-level policies guided by a sampling-based Probabilistic Roadmap (PRM) planner. We demonstrate that our framework can solve long-horizon navigation tasks using only local information. We evaluate our approach on partially-observed maze navigation with MuJoCo robots, including Ant, Point, and Humanoid. We show that Control Transformer can successfully navigate through mazes and transfer to unknown environments. Additionally, we apply our method to a differential drive robot (Turtlebot3) and show zero-shot sim2real transfer under noisy observations.

We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our adversaries do not win by playing Go well. Instead, they trick KataGo into making serious blunders. Our attack transfers zero-shot to other superhuman Go-playing AIs, and is comprehensible to the extent that human experts can implement it without algorithmic assistance to consistently beat superhuman AIs. The core vulnerability uncovered by our attack persists even in KataGo agents adversarially trained to defend against our attack. Our results demonstrate that even superhuman AI systems may harbor surprising failure modes. Example games are available https://goattack.far.ai/.