相关论文: Differentiable Information Enhanced Model-Based Re…

Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics. It has been widely adopted in the research of robotics,…

Meta-reinforcement learning algorithms provide a data-driven way to acquire policies that quickly adapt to many tasks with varying rewards or dynamics functions. However, learned meta-policies are often effective only on the exact task…

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynamics modeling and the subsequent planning algorithm, and as a…

Developing effective Multi-Agent Systems (MAS) is critical for many applications requiring collaboration and coordination with humans. Despite the rapid advance of Multi-Agent Deep Reinforcement Learning (MADRL) in cooperative MAS, one…

Learning to reach goal states and learning diverse skills through mutual information (MI) maximization have been proposed as principled frameworks for self-supervised reinforcement learning, allowing agents to acquire broadly applicable…

Many real-world applications can be formulated as multi-agent cooperation problems, such as network packet routing and coordination of autonomous vehicles. The emergence of deep reinforcement learning (DRL) provides a promising approach for…

Model-based reinforcement learning (RL) is anticipated to exhibit higher sample efficiency compared to model-free RL by utilizing a virtual environment model. However, it is challenging to obtain sufficiently accurate representations of the…

Distributionally Robust Reinforcement Learning (DR-RL) aims to derive a policy optimizing the worst-case performance within a predefined uncertainty set. Despite extensive research, previous DR-RL algorithms have predominantly favored…

In scheduling problems common in the industry and various real-world scenarios, responding in real-time to disruptive events is essential. Recent methods propose the use of deep reinforcement learning (DRL) to learn policies capable of…

Reinforcement learning (RL) is currently one of the most prominent methods for optimizing dynamical systems, with breakthrough results across various fields. The framework is based on the concept of a Markov decision process (MDP), leading…

Traditional Evidence Deep Learning (EDL) methods rely on static hyperparameter for uncertainty calibration, limiting their adaptability in dynamic data distributions, which results in poor calibration and generalization in high-risk…

World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are independent or sparsely dependent on action signals often exist,…

Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Imitation Learning (IL) has proven highly effective for robotic and control tasks where manually designing reward functions or explicit controllers is infeasible. However, standard IL methods implicitly assume that the environment dynamics…

We consider the problem of learning a control policy that is robust against the parameter mismatches between the training environment and testing environment. We formulate this as a distributionally robust reinforcement learning (DR-RL)…

Multi-Agent Reinforcement Learning (MARL) has enjoyed significant recent progress thanks, in part, to the integration of deep learning techniques for modeling interactions in complex environments. This is naturally starting to benefit…

Deep reinforcement learning (DRL) has had success across various domains, but applying it to environments with constraints remains challenging due to poor sample efficiency and slow convergence. Recent literature explored incorporating…

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…

Many methods for Model-based Reinforcement learning (MBRL) in Markov decision processes (MDPs) provide guarantees for both the accuracy of the model they can deliver and the learning efficiency. At the same time, state abstraction…