Search Results for author:
Found 5 papers, 3 papers with code
Improved weight initialization for deep and narrow feedforward neural network
The problem of \textquotedblleft dying ReLU," where ReLU neurons become inactive and yield zero output, presents a significant challenge in the training of deep neural networks with ReLU activation function.
Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion
In this work, we propose a novel reinforcement learning framework for training neural network controllers for complex robotic systems consisting of both rewards and constraints.
DiffFace: Diffusion-based Face Swapping with Facial Guidance
In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending.
Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation
For autonomous quadruped robot navigation in various complex environments, a typical SOTA system is composed of four main modules -- mapper, global planner, local planner, and command-tracking controller -- in a hierarchical manner.
Learning multiple gaits of quadruped robot using hierarchical reinforcement learning
There is a growing interest in learning a velocity command tracking controller of quadruped robot using reinforcement learning due to its robustness and scalability.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
