Related papers: Beyond Tabula-Rasa: a Modular Reinforcement Learni…
Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD). Despite…
Meta-reinforcement learning (meta-RL) aims to quickly solve new tasks by leveraging knowledge from prior tasks. However, previous studies often assume a single mode homogeneous task distribution, ignoring possible structured heterogeneity…
Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges,…
Reinforcement learning (RL) excels in various applications but struggles in dynamic environments where the underlying Markov decision process evolves. Continual reinforcement learning (CRL) enables RL agents to continually learn and adapt…
We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm,…
Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex…
This paper explores the integration of incremental curriculum learning (ICL) with deep reinforcement learning (DRL) techniques to facilitate mobile robot navigation through task-based human instruction. By adopting a curriculum that mirrors…
We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on…
Navigating rugged landscapes poses significant challenges for legged locomotion. Multi-legged robots (those with 6 and greater) offer a promising solution for such terrains, largely due to their inherent high static stability, resulting…
Deep reinforcement learning has shown promise in discrete domains requiring complex reasoning, including games such as Chess, Go, and Hanabi. However, this type of reasoning is less often observed in long-horizon, continuous domains with…
Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over…
Robotic insertion tasks are characterized by contact and friction mechanics, making them challenging for conventional feedback control methods due to unmodeled physical effects. Reinforcement learning (RL) is a promising approach for…
Model-based reinforcement learning (MBRL) is recognized with the potential to be significantly more sample-efficient than model-free RL. How an accurate model can be developed automatically and efficiently from raw sensory inputs (such as…
Deep reinforcement learning (RL) can enable robots to autonomously acquire complex behaviors, such as legged locomotion. However, RL in the real world is complicated by constraints on efficiency, safety, and overall training stability,…
Current embodied reasoning agents struggle to plan for long-horizon tasks that require to physically interact with the world to obtain the necessary information (e.g. 'sort the objects from lightest to heaviest'). The improvement of the…
Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of…
We present a reinforcement learning (RL) framework in which the learned policy comes with a machine-checkable certificate of provable adversarial robustness. Our approach, called CAROL, learns a model of the environment. In each learning…
Complex high-dimensional spaces with high Degree-of-Freedom and complicated action spaces, such as humanoid robots equipped with dexterous hands, pose significant challenges for reinforcement learning (RL) algorithms, which need to wisely…
Studies that broaden drone applications into complex tasks require a stable control framework. Recently, deep reinforcement learning (RL) algorithms have been exploited in many studies for robot control to accomplish complex tasks.…
For real-world deployments, it is critical to allow robots to navigate in complex environments autonomously. Traditional methods usually maintain an internal map of the environment, and then design several simple rules, in conjunction with…