5 papers
Adapting Reinforcement Learning for Path Planning in Constrained Parking Scenarios
Feng Tao, Luca Paparusso, Chenyi Gu +6
Real-time path planning in constrained environments remains a fundamental challenge for autonomous systems. Traditional classical planners, while effective under perfect perception…
Learning a Single Policy for Diverse Behaviors on a Quadrupedal Robot using Scalable Motion Imitation
Arnaud Klipfel, Nitish Sontakke, Ren Liu +1
Learning various motor skills for quadrupedal robots is a challenging problem that requires careful design of task-specific mathematical models or reward descriptions. In this work…
A stochastic three-block splitting algorithm and its application to quantized deep neural networks
Fengmiao Bian, Ren Liu, Xiaoqun Zhang
Deep neural networks (DNNs) have made great progress in various fields. In particular, the quantized neural network is a promising technique making DNNs compatible on resource-limi…
PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotion
Ren Liu, Nitish Sontakke, Sehoon Ha
Deep reinforcement learning (deep RL) has emerged as an effective tool for developing controllers for legged robots. However, vanilla deep RL often requires a tremendous amount of…
Semi-Implicit Back Propagation
Ren Liu, Xiaoqun Zhang
Neural network has attracted great attention for a long time and many researchers are devoted to improve the effectiveness of neural network training algorithms. Though stochastic…