Adversary A3C for Robust Reinforcement Learning

no code implementations • ICLR 2018 • Zhaoyuan Gu, Zhenzhong Jia, Howie Choset

Asynchronous Advantage Actor Critic (A3C) is an effective Reinforcement Learning (RL) algorithm for a wide range of tasks, such as Atari games and robot control.

Atari Games reinforcement-learning +1

Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints

no code implementations • 26 Nov 2019 • Jingliang Duan, Zhengyu Liu, Shengbo Eben Li, Qi Sun, Zhenzhong Jia, Bo Cheng

CADP linearizes the constrained optimization problem locally into a quadratically constrained linear programming problem, and then obtains the optimal update of the policy network by solving its dual problem.

MRS-VPR: a multi-resolution sampling based global visual place recognition method

no code implementations • 26 Feb 2019 • Peng Yin, Rangaprasad Arun Srivatsan, Yin Chen, Xueqian Li, Hongda Zhang, Lingyun Xu, Lu Li, Zhenzhong Jia, Jianmin Ji, Yuqing He

We propose MRS-VPR, a multi-resolution, sampling-based place recognition method, which can significantly improve the matching efficiency and accuracy in sequential matching.

Loop Closure Detection Visual Navigation +1