5 papers
Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization
Buqing Nie, Yangqing Fu, Jingtian Ji +1
Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different pertur…
Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots
Yang Zhang, Buqing Nie, Zhanxiang Cao +2
Reinforcement Learning (RL)-based methods have significantly improved the locomotion performance of legged robots. However, these motion policies face significant challenges when d…
Select before Act: Spatially Decoupled Action Repetition for Continuous Control
Buqing Nie, Yangqing Fu, Yue Gao
Reinforcement Learning (RL) has achieved remarkable success in various continuous control tasks, such as robot manipulation and locomotion. Different to mainstream RL which makes d…
Improve Robustness of Reinforcement Learning against Observation Perturbations via Lipschitz Policy Networks
Buqing Nie, Jingtian Ji, Yangqing Fu +1
Deep Reinforcement Learning (DRL) has achieved remarkable advances in sequential decision tasks. However, recent works have revealed that DRL agents are susceptible to slight pertu…
Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction
Yangqing Fu, Ming Sun, Buqing Nie +1
Monte Carlo Tree Search (MCTS) algorithms such as AlphaGo and MuZero have achieved superhuman performance in many challenging tasks. However, the computational complexity of MCTS-b…