相关论文: Feudal Reinforcement Learning by Reading Manuals

When we design and deploy an Reinforcement Learning (RL) agent, reward functions motivates agents to achieve an objective. An incorrect or incomplete specification of the objective can result in behavior that does not align with human…

Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but…

Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially. One of the largest obstacles to CRL is that the…

Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hierarchical…

The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL). Optimisation via RL is highly susceptible to sample inefficiency and instability. The hierarchical approach called…

Human beings, even small children, quickly become adept at figuring out how to use applications on their mobile devices. Learning to use a new app is often achieved via trial-and-error, accelerated by transfer of knowledge from past…

Parallel Reinforcement Learning (RL) frameworks are essential for mapping RL workloads to multiple computational resources, allowing for faster generation of samples, estimation of values, and policy improvement. These computational…

This paper establishes directionality reinforcement learning (DRL) technique to propose the complete decentralized multi-agent reinforcement learning method which can achieve cooperation based on each agent's learning: no communication and…

Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoals to a lower level has been shown to enable fast learning…

Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning…

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose…

Advancements in reinforcement learning (RL) have been remarkable in recent years. However, the limitations of traditional training methods have become increasingly evident, particularly in meta-RL settings where agents face new, unseen…

Interactive reinforcement learning (IRL) extends traditional reinforcement learning (RL) by allowing an agent to interact with parent-like trainers during a task. In this paper, we present an IRL approach using dynamic audio-visual input in…

We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative…

Reinforcement learning (RL) is frequently used to increase performance in text generation tasks, including machine translation (MT), notably through the use of Minimum Risk Training (MRT) and Generative Adversarial Networks (GAN). However,…

Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent…

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

Medical Large Vision-Language Models (Med-LVLMs) have shown strong potential in multimodal diagnostic tasks. However, existing single-agent models struggle to generalize across diverse medical specialties, limiting their performance. Recent…

Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning. However, the existing Hierarchical Reinforcement Learning…

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…