Related papers: G-Learner and GIRL: Goal Based Wealth Management w…
One of the biggest problems in itemset mining is the requirement of developing a data structure or algorithm, every time a user wants to extract a different type of itemsets. To overcome this, we propose a method, called Generic Itemset…
This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…
We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…
Zero Reinforcement Learning (Zero-RL) has proven to be an effective approach for enhancing the reasoning capabilities of large language models (LLMs) by directly applying reinforcement learning with verifiable rewards on pretrained models,…
Deep Reinforcement Learning (DRL) has shown its promising capabilities to learn optimal policies directly from trial and error. However, learning can be hindered if the goal of the learning, defined by the reward function, is "not optimal".…
Recent advances have shown that video generation models can enhance robot learning by deriving effective robot actions through inverse dynamics. However, these methods heavily depend on the quality of generated data and struggle with…
Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…
Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…
The theory of greedy low-rank learning (GLRL) aims to explain the impressive generalization capabilities of deep learning. It proves that stochastic gradient-based training implicitly regularizes neural networks towards low-rank solutions…
Goal-conditioned and Multi-Task Reinforcement Learning (GCRL and MTRL) address numerous problems related to robot learning, including locomotion, navigation, and manipulation scenarios. Recent works focusing on language-defined robotic…
Reinforcement learning (RL) techniques have shown great success in many challenging quantitative trading tasks, such as portfolio management and algorithmic trading. Especially, intraday trading is one of the most profitable and risky tasks…
Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \aka, graph flow model (GFM), has emerged due to its superior performance and flexible…
Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on…
We present new algorithms for inverse reinforcement learning (IRL, or inverse optimal control) in convex optimization settings. We argue that finite-space IRL can be posed as a convex quadratic program under a Bayesian inference framework…
Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns while minimizing risks using historical data. However,…
We study a class of reinforcement learning problems where the reward signals for policy learning are generated by an internal reward model that is dependent on and jointly optimized with the policy. This interdependence between the policy…
The common purpose of applying reinforcement learning (RL) to asset management is the maximization of profit. The extrinsic reward function used to learn an optimal strategy typically does not take into account any other preferences or…
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…
Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. However, heterogeneous data distributions over different…
As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and…