Collision avoidance algorithms for Autonomous Surface Vehicles (ASV) that follow the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) have been proposed in recent years. However, it may be difficult and unsafe to follow COLREGs in congested waters, where multiple ASVs are navigating in the presence of static obstacles and strong currents, due to the complex interactions. To address this problem, we propose a decentralized multi-ASV collision avoidance policy based on Distributional Reinforcement Learning, which considers the interactions among ASVs as well as with static obstacles and current flows. We evaluate the performance of the proposed Distributional RL based policy against a traditional RL-based policy and two classical methods, Artificial Potential Fields (APF) and Reciprocal Velocity Obstacles (RVO), in simulation experiments, which show that the proposed policy achieves superior performance in navigation safety, while requiring minimal travel time and energy. A variant of our framework that automatically adapts its risk sensitivity is also demonstrated to improve ASV safety in highly congested environments.

Value functions are a central component of deep reinforcement learning (RL). These functions, parameterized by neural networks, are trained using a mean squared error regression objective to match bootstrapped target values. However, scaling value-based RL methods that use regression to large networks, such as high-capacity Transformers, has proven challenging. This difficulty is in stark contrast to supervised learning: by leveraging a cross-entropy classification loss, supervised methods have scaled reliably to massive networks. Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions. We demonstrate that value functions trained with categorical cross-entropy significantly improves performance and scalability in a variety of domains. These include: single-task RL on Atari 2600 games with SoftMoEs, multi-task RL on Atari with large-scale ResNets, robotic manipulation with Q-transformers, playing Chess without search, and a language-agent Wordle task with high-capacity Transformers, achieving state-of-the-art results on these domains. Through careful analysis, we show that the benefits of categorical cross-entropy primarily stem from its ability to mitigate issues inherent to value-based RL, such as noisy targets and non-stationarity. Overall, we argue that a simple shift to training value functions with categorical cross-entropy can yield substantial improvements in the scalability of deep RL at little-to-no cost.

Artificial Intelligence for Theorem Proving has given rise to a plethora of benchmarks and methodologies, particularly in Interactive Theorem Proving (ITP). Research in the area is fragmented, with a diverse set of approaches being spread across several ITP systems. This presents a significant challenge to the comparison of methods, which are often complex and difficult to replicate. Addressing this, we present BAIT, a framework for fair and streamlined comparison of learning approaches in ITP. We demonstrate BAIT's capabilities with an in-depth comparison, across several ITP benchmarks, of state-of-the-art architectures applied to the problem of formula embedding. We find that Structure Aware Transformers perform particularly well, improving on techniques associated with the original problem sets. BAIT also allows us to assess the end-to-end proving performance of systems built on interactive environments. This unified perspective reveals a novel end-to-end system that improves on prior work. We also provide a qualitative analysis, illustrating that improved performance is associated with more semantically-aware embeddings. By streamlining the implementation and comparison of Machine Learning algorithms in the ITP context, we anticipate BAIT will be a springboard for future research.

Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks. Yet, the application of these skills in different domains remains restricted due to their inherent dependency on the datasets, which poses a challenge when attempting to learn a skill-based policy via RL for a target domain different from the datasets' domains. In this paper, we present a novel offline skill learning framework DuSkill which employs a guided Diffusion model to generate versatile skills extended from the limited skills in datasets, thereby enhancing the robustness of policy learning for tasks in different domains. Specifically, we devise a guided diffusion-based skill decoder in conjunction with the hierarchical encoding to disentangle the skill embedding space into two distinct representations, one for encapsulating domain-invariant behaviors and the other for delineating the factors that induce domain variations in the behaviors. Our DuSkill framework enhances the diversity of skills learned offline, thus enabling to accelerate the learning procedure of high-level policies for different domains. Through experiments, we show that DuSkill outperforms other skill-based imitation learning and RL algorithms for several long-horizon tasks, demonstrating its benefits in few-shot imitation and online RL.

Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to divide and distribute the subtasks between the participating agents to carry out the main task. In contrast, we propose to learn a human constraints model that, in addition, considers the diverse behaviors of different human operators. We consider a type of collaboration in a shared-autonomy fashion, where both a human operator and an assistive robot act simultaneously in the same task space that affects each other's actions. The task of the assistive agent is to augment the skill of humans to perform a shared task by supporting humans as much as possible, both in terms of reducing the workload and minimizing the discomfort for the human operator. Therefore, we propose an augmentative assistant agent capable of learning and adapting to human physical constraints, aligning its actions with the ergonomic preferences and limitations of the human operator.

A key challenge in realizing fault-tolerant quantum computers is circuit optimization. Focusing on the most expensive gates in fault-tolerant quantum computation (namely, the T gates), we address the problem of T-count optimization, i.e., minimizing the number of T gates that are needed to implement a given circuit. To achieve this, we develop AlphaTensor-Quantum, a method based on deep reinforcement learning that exploits the relationship between optimizing T-count and tensor decomposition. Unlike existing methods for T-count optimization, AlphaTensor-Quantum can incorporate domain-specific knowledge about quantum computation and leverage gadgets, which significantly reduces the T-count of the optimized circuits. AlphaTensor-Quantum outperforms the existing methods for T-count optimization on a set of arithmetic benchmarks (even when compared without making use of gadgets). Remarkably, it discovers an efficient algorithm akin to Karatsuba's method for multiplication in finite fields. AlphaTensor-Quantum also finds the best human-designed solutions for relevant arithmetic computations used in Shor's algorithm and for quantum chemistry simulation, thus demonstrating it can save hundreds of hours of research by optimizing relevant quantum circuits in a fully automated way.

Purpose: The treatment of cardiovascular diseases requires complex and challenging navigation of a guidewire and catheter. This often leads to lengthy interventions during which the patient and clinician are exposed to X-ray radiation. Deep Reinforcement Learning approaches have shown promise in learning this task and may be the key to automating catheter navigation during robotized interventions. Yet, existing training methods show limited capabilities at generalizing to unseen vascular anatomies, requiring to be retrained each time the geometry changes. Methods: In this paper, we propose a zero-shot learning strategy for three-dimensional autonomous endovascular navigation. Using a very small training set of branching patterns, our reinforcement learning algorithm is able to learn a control that can then be applied to unseen vascular anatomies without retraining. Results: We demonstrate our method on 4 different vascular systems, with an average success rate of 95% at reaching random targets on these anatomies. Our strategy is also computationally efficient, allowing the training of our controller to be performed in only 2 hours. Conclusion: Our training method proved its ability to navigate unseen geometries with different characteristics, thanks to a nearly shape-invariant observation space.

This paper presents our work to enhance the background music (BGM) in DareFightingICE by adding adaptive features. The adaptive BGM consists of three different categories of instruments playing the BGM of the winner sound design from the 2022 DareFightingICE Competition. The BGM adapts by changing the volume of each category of instruments. Each category is connected to a different element of the game. We then run experiments to evaluate the adaptive BGM by using a deep reinforcement learning AI agent that only uses audio as input (Blind DL AI). The results show that the performance of the Blind DL AI improves while playing with the adaptive BGM as compared to playing without the adaptive BGM.

Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents. Large Language Models (LLMs), with a wealth of world knowledge, can help RL agents learn quickly and adapt to distribution shifts. In this work, we introduce Language Guided Exploration (LGE) framework, which uses a pre-trained language model (called GUIDE ) to provide decision-level guidance to an RL agent (called EXPLORER). We observe that on ScienceWorld (Wang et al.,2022), a challenging text environment, LGE outperforms vanilla RL agents significantly and also outperforms other sophisticated methods like Behaviour Cloning and Text Decision Transformer.

Multitask Reinforcement Learning (MTRL) approaches have gained increasing attention for its wide applications in many important Reinforcement Learning (RL) tasks. However, while recent advancements in MTRL theory have focused on the improved statistical efficiency by assuming a shared structure across tasks, exploration--a crucial aspect of RL--has been largely overlooked. This paper addresses this gap by showing that when an agent is trained on a sufficiently diverse set of tasks, a generic policy-sharing algorithm with myopic exploration design like $\epsilon$-greedy that are inefficient in general can be sample-efficient for MTRL. To the best of our knowledge, this is the first theoretical demonstration of the "exploration benefits" of MTRL. It may also shed light on the enigmatic success of the wide applications of myopic exploration in practice. To validate the role of diversity, we conduct experiments on synthetic robotic control environments, where the diverse task set aligns with the task selection by automatic curriculum learning, which is empirically shown to improve sample-efficiency.