Reinforcement Learning
Sequential decision-making for the real world.
Reinforcement learning (RL) has provided solutions for several difficult sequential decision-making problems in games, locomotion, and robotics. At PFN, we aim to address challenges in reinforcement learning to enable real-world applications. Our research includes deep RL, safety, robotics, model-based RL, and imitation learning.
Publications
MANGA: Method Agnostic Neural-policy Generalization and Adaptation
ICRA 2020
By : Homanga Bharadhwaj, Shoichiro Yamaguchi, Shin-ichi Maeda
Behaviorally Diverse Traffic Simulation via Reinforcement Learning
IROS 2020
By : Shinya Shiroshita, Shirou Maruyama, Daisuke Nishiyama, Mario Castro, Karim Hamzaoui, Guy Rosman, Jonathan DeCastro, Kuan-Hui Lee, Adrien Gaidon
Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators
IROS 2020
By : Yasuhiro Fujita, Kota Uenishi, Avinash Ummadisingu, Prabhat Nagarajan, Shimpei Masuda, Mario Castro
Model-Based Reinforcement Learning via Meta-Policy Optimization
CoRL 2018
By : Ignasi Clavera, Jonas Rothfuss, John Schulman, Yasuhiro Fujita, Tamim Asfour, Pieter Abbeel
