the archive

#deep reinforcement learning

9 results

cs.RO2019

Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning

Yuan Gao, Fangkai Yang, Martin Frisk +3

The paper introduces a deep reinforcement learning framework that trains a robot to approach small groups of people in a socially appropriate way using simulated learning stages, a…

#social robot navigation#deep reinforcement learning#human-robot interaction#group approach behavior

cs.NI2019

Deep Reinforcement Learning for Network Slicing with Heterogeneous Resource Requirements and Time Varying Traffic Dynamics

Jaehoon Koo, Veena B. Mendiratta, Muntasir Raihan Rahman +1

The paper proposes a deep reinforcement learning method to dynamically allocate heterogeneous resources for network slicing in 5G/SDN/NFV environments, showing improved utilization…

#network slicing#deep reinforcement learning#resource allocation#5g

cs.RO2019

Learning to Grasp from 2.5D images: a Deep Reinforcement Learning Approach

Alessia Bertugli, Paolo Galeone

The paper presents a deep reinforcement learning method that uses only 2.5D depth images to train a robot with a vacuum gripper to grasp planar blocks, achieving accurate pose esti…

#deep reinforcement learning#grasping#2.5d depth images#robotic manipulation

cs.LG2019

AlphaSeq: Sequence Discovery with Deep Reinforcement Learning

Yulin Shao, Soung Chang Liew, Taotao Wang

The paper presents AlphaSeq, a deep reinforcement learning framework that treats sequence design as a symbol‑filling game and learns to generate sequences with desired properties,…

#deep reinforcement learning#sequence design#markov decision process#code construction

cs.LG2019

Improving Deep Reinforcement Learning in Minecraft with Action Advice

Spencer Frazier, Mark Riedl

The paper investigates how limited human-provided action advice can improve deep reinforcement learning agents' performance in visually aliased 3D environments like Minecraft.

#deep reinforcement learning#interactive machine learning#action advice#visual aliasing

cond-mat.soft2019

Efficient Navigation of Colloidal Robots in an Unknown Environment via Deep Reinforcement Learning

Yuguang Yang, Michael A. Bevan, Bo Li

The paper presents a model‑free deep reinforcement learning method that trains active colloidal robots to navigate unknown, obstacle‑filled environments using only local sensory in…

#colloidal robots#deep reinforcement learning#navigation#obstacle avoidance

cs.NI2019

Learn to Allocate Resources in Vehicular Networks

Liang Wang, Hao Ye, Le Liang +1

The paper proposes a hybrid deep learning framework that combines centralized decision making with distributed resource sharing to allocate spectrum in vehicle-to-everything (V2X)…

#vehicular networks#resource allocation#deep reinforcement learning#centralized-decentralized architecture

cs.RO2019

Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning

Tianyu Shi, Pin Wang, Xuxin Cheng +2

The paper proposes a deep reinforcement learning approach using DQN to decide when and how to perform lane changes, and implements trajectory generation with Pure Pursuit control f…

#deep reinforcement learning#lane change decision#trajectory planning#control systems

cs.DC2019

DeepPlace: Learning to Place Applications in Multi-Tenant Clusters

Subrata Mitra, Shanka Subhra Mondal, Nikhil Sheoran +3

DeepPlace is a scheduler that uses deep reinforcement learning to automatically learn placement policies for applications in multi-tenant clusters, aiming to reduce resource conten…

#resource scheduling#deep reinforcement learning#multi-tenant clusters#application placement