相关论文: CARL: Controllable Agent with Reinforcement Learni…

Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on…

In multi-agent navigation, agents need to move towards their goal locations while avoiding collisions with other agents and static obstacles, often without communication with each other. Existing methods compute motions that are optimal…

In this work, we present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM learns a representation of…

Cooperative grasping and transportation require effective coordination to complete the task. This study focuses on the approach leveraging force-sensing feedback, where robots use sensors to detect forces applied by others on an object to…

We study multi-agent reinforcement learning (MARL) for tasks in complex high-dimensional environments, such as autonomous driving. MARL is known to suffer from the \textit{partial observability} and \textit{non-stationarity} issues. To…

While Reinforcement Learning has made great strides towards solving ever more complicated tasks, many algorithms are still brittle to even slight changes in their environment. This is a limiting factor for real-world applications of RL.…

Lane change decision-making is a complex task due to intricate vehicle-vehicle and vehicle-infrastructure interactions. Existing algorithms for lane-change control often depend on vehicles with a certain level of autonomy (e.g., autonomous…

Robust reinforcement learning agents using high-dimensional observations must be able to identify relevant state features amidst many exogeneous distractors. A representation that captures controllability identifies these state elements by…

Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose…

Sampling-based trajectory planners are widely used for agile autonomous driving due to their ability to generate fast, smooth, and kinodynamically feasible trajectories. However, their behavior is often governed by a cost function with…

We consider the problem of robust multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents, mainly those trained in a centralized way, can be brittle because they can adopt policies that…

Automated vehicle control using reinforcement learning (RL) has attracted significant attention due to its potential to learn driving policies through environment interaction. However, RL agents often face training challenges in sample…

Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such…

Persistent monitoring of dynamic targets is essential in real-world applications such as disaster response, environmental sensing, and wildlife conservation, where mobile agents must continuously gather information under uncertainty. We…

Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generate flexible and diverse behaviors in cyberspace; however,…

Urban traffic congestion, particularly at intersections, significantly affects travel time, fuel consumption, and emissions. Traditional fixed-time signal control systems often lack the adaptability to effectively manage dynamic traffic…

Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive…

Using Reinforcement Learning (RL) to learn new robotic tasks from scratch is often inefficient. Leveraging prior knowledge has the potential to significantly enhance learning efficiency, which, however, raises two critical challenges: how…

The capability to learn and adapt to changes in the driving environment is crucial for developing autonomous driving systems that are scalable beyond geo-fenced operational design domains. Deep Reinforcement Learning (RL) provides a…

In real-world environments, autonomous agents rely on their egocentric observations. They must learn adaptive strategies to interact with others who possess mixed motivations, discernible only through visible cues. Several Multi-Agent…