Related papers: Automatic Trade-off Adaptation in Offline RL

Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a system's operation, but no direct access to the system when learning a policy. Recent…

We consider the offline reinforcement learning (RL) setting where the agent aims to optimize the policy solely from the data without further environment interactions. In offline RL, the distributional shift becomes the primary source of…

Distributed transaction processing often involves multiple rounds of cross-node communications, and therefore tends to be slow. To improve performance, existing approaches convert distributed transactions into single-node transactions by…

Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a…

In recent years, significant progress has been made in multi-objective reinforcement learning (RL) research, which aims to balance multiple objectives by incorporating preferences for each objective. In most existing studies, specific…

Reconfigurable optical topologies are emerging as a promising technology to improve the efficiency of datacenter networks. This paper considers the problem of scheduling opportunistic links in such reconfigurable datacenters. We study the…

The stable combination of optimal feedback policies with online learning is studied in a new control-theoretic framework for uncertain nonlinear systems. The framework can be systematically used in transfer learning and sim-to-real…

In this paper, we propose an online-matching-based model to study the assignment problems arising in a wide range of online-matching markets, including online recommendations, ride-hailing platforms, and crowdsourcing markets. It features…

We introduce and study online conversion with switching costs, a family of online problems that capture emerging problems at the intersection of energy and sustainability. In this problem, an online player attempts to purchase…

The vast majority of optimization and online learning algorithms today require some prior information about the data (often in the form of bounds on gradients or on the optimal parameter value). When this information is not available, these…

We take the novel perspective of incorporating offline RL algorithms as subroutines of tabula rasa online RL. This is feasible because an online learning agent can repurpose its historical interactions as offline dataset. We formalize this…

Continual adaptation is essential for general autonomous agents. For example, a household robot pretrained with a repertoire of skills must still adapt to unseen tasks specific to each household. Motivated by this, building upon…

This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment. A central question boils down to how to efficiently utilize…

In Federated Learning (FL), a framework to train machine learning models across distributed data, well-known algorithms like FedAvg tend to have slow convergence rates, resulting in high communication costs during training. To address this…

In this work we study the problem of using machine-learned predictions to improve the performance of online algorithms. We consider two classical problems, ski rental and non-clairvoyant job scheduling, and obtain new online algorithms that…

Online tuning of real-world plants is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods,…

Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets. However, as many real-world scenarios involve interaction among multiple agents, it is important to…

Reward design has been one of the central challenges for real world reinforcement learning (RL) deployment, especially in settings with multiple objectives. Preference-based RL offers an appealing alternative by learning from human…

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online. A smooth transfer of the policy matters in safe real-world deployment. Besides, fast…