Multi-agent active information gathering in discrete and continuous-state decentralized POMDPs by policy graph improvement von Lauri, Mikko, Pajarinen, Joni, Peters, Jan

Volltext

Long-Term Visitation Value for Deep Exploration in Sparse-Reward Reinforcement Learning von Parisi, Simone, Tateo, Davide, Hensel, Maximilian, D’Eramo, Carlo, Peters, Jan, Pajarinen, Joni

Volltext

Visual Rewards From Observation for Sequential Tasks: Autonomous Pile Loading von Strokina, Nataliya, Yang, Wenyan, Pajarinen, Joni, Serbenyuk, Nikolay, Kämäräinen, Joni, Ghabcheloo, Reza

Volltext

Robotic manipulation of multiple objects as a POMDP von Pajarinen, Joni, Kyrki, Ville

Volltext

POMDP Planning Under Object Composition Uncertainty: Application to Robotic Manipulation von Pajarinen, Joni, Lundell, Jens, Kyrki, Ville

Volltext

On the Benefit of Optimal Transport for Curriculum Reinforcement Learning von Klink, Pascal, D'Eramo, Carlo, Peters, Jan, Pajarinen, Joni

Volltext

Expectation Maximization for Average Reward Decentralized POMDPs von Pajarinen, Joni, Peltonen, Jaakko

Volltext

A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search von Dam, Tuan, D'Eramo, Carlo, Peters, Jan, Pajarinen, Joni

Volltext

Partially Observable Markov Decision Processes in Robotics: A Survey von Lauri, Mikko, Hsu, David, Pajarinen, Joni

Volltext

Reinforcement Learning Based Underwater Wireless Optical Communication Alignment for Autonomous Underwater Vehicles von Weng, Yang, Pajarinen, Joni, Akrour, Riad, Matsuda, Takumi, Peters, Jan, Maki, Toshihiro

Volltext

Monte-Carlo Robot Path Planning von Dam, Tuan, Chalvatzaki, Georgia, Peters, Jan, Pajarinen, Joni

Volltext

Pointing Error Control of Underwater Wireless Optical Communication on Mobile Platform von Weng, Yang, Matsuda, Takumi, Sekimori, Yuki, Pajarinen, Joni, Peters, Jan, Maki, Toshihiro

Volltext

Compatible natural gradient policy search von Pajarinen, Joni, Thai, Hong Linh, Akrour, Riad, Peters, Jan, Neumann, Gerhard

Volltext

Autonomous underwater vehicle link alignment control in unknown environments using reinforcement learning von Weng, Yang, Chun, Sehwa, Ohashi, Masaki, Matsuda, Takumi, Sekimori, Yuki, Pajarinen, Joni, Peters, Jan, Maki, Toshihiro

Volltext

Nonlinear Model Learning for Compensation and Feedforward Control of Real-World Hydraulic Actuators Using Gaussian Processes von Taheri, Abdolreza, Gustafsson, Pelle, Rosth, Marcus, Ghabcheloo, Reza, Pajarinen, Joni

Volltext

Establishment of line-of-sight optical links between autonomous underwater vehicles: Field experiment and performance validation von Weng, Yang, Matsuda, Takumi, Sekimori, Yuki, Pajarinen, Joni, Peters, Jan, Maki, Toshihiro

Volltext

Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization von Lauri, Mikko, Pajarinen, Joni, Peters, Jan, Frintrop, Simone

Volltext

Learning-Based Propulsion Control for Amphibious Quadruped Robots With Dynamic Adaptation to Changing Environment von Yao, Qingfeng, Meng, Linghan, Zhang, Qifeng, Zhao, Jing, Pajarinen, Joni, Wang, Xiaohui, Li, Zhibin, Wang, Cong

Volltext

Imitation-Enhanced Reinforcement Learning With Privileged Smooth Transition for Hexapod Locomotion von Zhang, Zhelin, Liu, Tie, Ding, Liang, Wang, Haoyu, Xu, Peng, Yang, Huaiguang, Gao, Haibo, Deng, Zongquan, Pajarinen, Joni

Volltext

Probabilistic Approach to Physical Object Disentangling von Pajarinen, Joni, Arenz, Oleg, Peters, Jan, Neumann, Gerhard

Volltext