Related papers: TwinRL: Digital Twin-Driven Reinforcement Learning…

Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied applications. The agentic paradigm promises that VLMs can use a wide variety of…

We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics using traditional robotic tools that extend state-of-the-art DRL implementations and provide an end-to-end approach which trains a robot directly from…

Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose…

The goal of an offline reinforcement learning (RL) algorithm is to learn optimal polices using historical (offline) data, without access to the environment for online exploration. One of the main challenges in offline RL is the distribution…

Reinforcement learning (RL) is a paradigm increasingly used to align large language models. Popular RL algorithms utilize multiple workers and can be modeled as a graph, where each node is the status of a worker and each edge represents…

Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recipe for data-driven decision-making. While sensible, this…

In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL)…

Direct evaluation of LLMs on benchmarks can be misleading because comparatively strong performance may reflect task familiarity rather than capability. The train-before-test approach controls for task familiarity by giving each model…

Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of…

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models.…

This paper presents a Pre-Training Deep Reinforcement Learning(DRL) for avoidance navigation without map for mobile robots which map raw sensor data to control variable and navigate in an unknown environment. The efficient offline training…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation. However, existing post-training methods face a dilemma between stability and exploration: Supervised Fine-Tuning (SFT) is constrained by…

Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online…

Next Generation (NextG) networks are expected to support demanding tactile internet applications such as augmented reality and connected autonomous vehicles. Whereas recent innovations bring the promise of larger link capacity, their…

Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world…

Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essential for the success of RL. We observe that for complex…

High-speed online trajectory planning for UAVs poses a significant challenge due to the need for precise modeling of complex dynamics while also being constrained by computational limitations. This paper presents a multi-fidelity…

Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes…

Deep reinforcement learning (DRL) methods have demonstrated potential for autonomous navigation and obstacle avoidance of unmanned ground vehicles (UGVs) in crowded environments. Most existing approaches rely on single-frame observation and…

Internet of Things (IoT) devices are available in a multitude of scenarios, and provide constant, contextual data which can be leveraged to automatically reconfigure and optimize smart environments. To realize this vision, Artificial…