相关论文: Flexible Option Learning

Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…

Reinforcement learning (RL) is a sub-domain of machine learning, mainly concerned with solving sequential decision-making problems by a learning agent that interacts with the decision environment to improve its behavior through the reward…

With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining…

Hierarchical abstractions, also known as options -- a type of temporally extended action (Sutton et. al. 1999) that enables a reinforcement learning agent to plan at a higher level, abstracting away from the lower-level details. In this…

Algorithmic recourse seeks to provide individuals with actionable recommendations that increase their chances of receiving favorable outcomes from automated decision systems (e.g., loan approvals). While prior research has emphasized…

Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL…

Transferring high-level knowledge from a source task to a target task is an effective way to expedite reinforcement learning (RL). For example, propositional logic and first-order logic have been used as representations of such knowledge.…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

Offline reinforcement learning (RL) holds promise as a means to learn high-reward policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching…

In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A…

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL,…

Optimization problems characterized by both discrete and continuous variables are common across various disciplines, presenting unique challenges due to their complex solution landscapes and the difficulty of navigating mixed-variable…

The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments. It addresses such goals by…

Reinforcement Learning (RL) bears the promise of being a game-changer in many applications. However, since most of the literature in the field is currently focused on opaque models, the use of RL in high-stakes scenarios, where…

Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a…

Real-world sequential decision-making often involves parameterized action spaces that require both, decisions regarding discrete actions and decisions about continuous action parameters governing how an action is executed. Existing…

Recently, robust reinforcement learning (RL) methods against input observation have garnered significant attention and undergone rapid evolution due to RL's potential vulnerability. Although these advanced methods have achieved reasonable…

Option-critic learning is a general-purpose reinforcement learning (RL) framework that aims to address the issue of long term credit assignment by leveraging temporal abstractions. However, when dealing with extended timescales, discounting…