相关论文: Q-Value Weighted Regression: Reinforcement Learnin…

Model-based offline reinforcement learning (RL) is a compelling approach that addresses the challenge of learning from limited, static data by generating imaginary trajectories using learned models. However, these approaches often struggle…

Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted…

This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with…

In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…

Ensuring strict safety guarantees is the paramount challenge for emerging 5G/6G wireless systems, particularly as they increasingly govern mission-critical applications ranging from autonomous UAV swarms to industrial automation. While deep…

Heavy-tailed high-dimensional data are commonly encountered in various scientific fields and pose great challenges to modern statistical analysis. A natural procedure to address this problem is to use penalized quantile regression with…

We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction. The framework mitigates the challenges that arise…

Offline reinforcement learning (RL) enables policy learning from static data but often suffers from poor coverage of the state-action space and distributional shift problems. This problem can be addressed by allowing limited online…

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…

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…

We propose a novel offline reinforcement learning (offline RL) approach, introducing the Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation (DIAR) framework. We address two key challenges in offline RL: out-of-distribution…

Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on algorithmic advancements, ignoring that many low-level…

Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training approach that combines offline imitation learning with…

Predicting a sequence of actions has been crucial in the success of recent behavior cloning algorithms in robotics. Can similar ideas improve reinforcement learning (RL)? We answer affirmatively by observing that incorporating action…

Deep Reinforcement Learning (RL) is well known for being highly sensitive to hyperparameters, requiring practitioners substantial efforts to optimize them for the problem at hand. This also limits the applicability of RL in real-world…

Penalized quantile regression (QR) is widely used for studying the relationship between a response variable and a set of predictors under data heterogeneity in high-dimensional settings. Compared to penalized least squares, scalable…

Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key challenge, however, is learning an accurate critic in large state--action spaces with limited…

Many problems, such as online ad display, can be formulated as online bipartite matching. The crucial challenge lies in the nature of sequentially-revealed online item information, based on which we make irreversible matching decisions at…

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component…

While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors…