相关论文: Critic-Guided Decision Transformer for Offline Rei…

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned…

Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BERT, are often employed to encode the trajectories. However,…

Reinforcement learning (RL) in robotics faces significant hurdles regarding sample efficiency and generalization across varying goals. While Offline RL mitigates the need for costly online interactions, its integration with goal-conditioned…

Offline Reinforcement Learning (RL) is structured to derive policies from static trajectory data without requiring real-time environment interactions. Recent studies have shown the feasibility of framing offline RL as a sequence modeling…

Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline paradigms. Online methods, such as RL-based alignment, can…

Decision Transformers (DTs) have emerged as a powerful framework for sequential decision making by formulating offline reinforcement learning (RL) as a sequence modeling problem. However, extending DTs to online settings with pure RL…

Decision Transformer (DT), which integrates reinforcement learning (RL) with the transformer model, introduces a novel approach to offline RL. Unlike classical algorithms that take maximizing cumulative discounted rewards as objective, DT…

Decision Transformer (DT), as one of the representative Reinforcement Learning via Supervised Learning (RvS) methods, has achieved strong performance in offline learning tasks by leveraging the powerful Transformer architecture for…

Despite some successful applications of goal-driven navigation, existing deep reinforcement learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled…

Transformer models have achieved remarkable empirical successes, largely due to their in-context learning capabilities. Inspired by this, we explore training an autoregressive transformer for in-context reinforcement learning (ICRL). In…

Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes. However, a challenge that often arises is the trade-off between both the computational efficiency of the…

General Value Function (GVF) is a powerful tool to represent both the {\em predictive} and {\em retrospective} knowledge in reinforcement learning (RL). In practice, often multiple interrelated GVFs need to be evaluated jointly with…

In the realm of online advertising, advertisers partake in ad auctions to obtain advertising slots, frequently taking advantage of auto-bidding tools provided by demand-side platforms. To improve the automation of these bidding systems, we…

In reinforcement learning (RL), offline learning decoupled learning from data collection and is useful in dealing with exploration-exploitation tradeoff and enables data reuse in many applications. In this work, we study two offline…

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…

In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditioned reinforcement learning (GCRL) problems, where the aim is…

Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the risk associated with different actions.…

The deployment of unmanned aerial vehicles (UAVs) for reliable and energy-efficient data collection from spatially distributed devices holds great promise in supporting diverse Internet of Things (IoT) applications. Nevertheless, the…

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

Driven by recent advances in sensing and computing, deep reinforcement learning (DRL) technologies have shown great potential for addressing distribution system restoration (DSR) under uncertainty. However, their data-intensive nature and…