Related papers: Efficient Replay Memory Architectures in Multi-Age…
The common pipeline in autonomous driving systems is highly modular and includes a perception component which extracts lists of surrounding objects and passes these lists to a high-level decision component. In this case, leveraging the…
End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans. However, it is still difficult to learn stably and efficiently because the learning method usually uses a nonlinear function…
Machine learning, artificial intelligence and especially deep learning based approaches are often used to simplify or eliminate the burden of programming industrial robots. Using these approaches robots inherently learn a skill instead of…
A core aspect of human intelligence is the ability to learn new tasks quickly and switch between them flexibly. Here, we describe a modular continual reinforcement learning paradigm inspired by these abilities. We first introduce a visual…
Humans navigate unfamiliar environments using episodic simulation and episodic memory, which facilitate a deeper understanding of the complex relationships between environments and objects. Developing an imaginative memory system inspired…
We approach the task of network congestion control in datacenters using Reinforcement Learning (RL). Successful congestion control algorithms can dramatically improve latency and overall network throughput. Until today, no such…
An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematical programming…
Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and…
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone…
Partially observed control problems are a challenging aspect of reinforcement learning. We extend two related, model-free algorithms for continuous control -- deterministic policy gradient and stochastic value gradient -- to solve partially…
Several studies have employed reinforcement learning (RL) to address the challenges of regional adaptive traffic signal control (ATSC) and achieved promising results. In this field, existing research predominantly adopts multi-agent…
Traffic signal control is of critical importance for the effective use of transportation infrastructures. The rapid increase of vehicle traffic and changes in traffic patterns make traffic signal control more and more challenging.…
Reinforcement learning has received high research interest for developing planning approaches in automated driving. Most prior works consider the end-to-end planning task that yields direct control commands and rarely deploy their algorithm…
Ensuring transportation systems are efficient is a priority for modern society. Technological advances have made it possible for transportation systems to collect large volumes of varied data on an unprecedented scale. We propose a traffic…
Intersections are essential road infrastructures for traffic in modern metropolises. However, they can also be the bottleneck of traffic flows as a result of traffic incidents or the absence of traffic coordination mechanisms such as…
The rapid development of autonomous vehicles (AVs) holds vast potential for transportation systems through improved safety, efficiency, and access to mobility. However, the progression of these impacts, as AVs are adopted, is not well…
Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning…
Event-triggered control provides a mechanism for avoiding excessive use of constrained communication bandwidth in networked multi-agent systems. However, most existing methods rely on accurate system models, which may be unavailable in…
Traffic signal controllers play an essential role in today's traffic system. However, the majority of them currently is not sufficiently flexible or adaptive to generate optimal traffic schedules. In this paper we present an approach to…