Search Results for author: Xinyang Gu

Found 5 papers, 2 papers with code

Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning

1 code implementation26 Aug 2024 Xinyang Gu, Yen-Jen Wang, Xiang Zhu, Chengming Shi, Yanjiang Guo, Yichen Liu, Jianyu Chen

In this work, we introduce Denoising World Model Learning (DWL), an end-to-end reinforcement learning framework for humanoid locomotion control, which demonstrates the world's first humanoid robot to master real-world challenging terrains such as snowy and inclined land in the wild, up and down stairs, and extremely uneven terrains.

Denoising reinforcement-learning +1

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer

1 code implementation8 Apr 2024 Xinyang Gu, Yen-Jen Wang, Jianyu Chen

Humanoid-Gym is an easy-to-use reinforcement learning (RL) framework based on Nvidia Isaac Gym, designed to train locomotion skills for humanoid robots, emphasizing zero-shot transfer from simulation to the real-world environment.

MuJoCo Physical Simulations +1

Soft Q Network

no code implementations20 Dec 2019 Jingbin Liu, Shuai Liu, Xinyang Gu

Deep Q Network (DQN) is a very successful algorithm, yet the inherent problem of reinforcement learning, i. e. the exploit-explore balance, remains.

Q-Learning

Policy Optimization Reinforcement Learning with Entropy Regularization

no code implementations2 Dec 2019 Jingbin Liu, Xinyang Gu, Shuai Liu

We introduce a local action variance for policy network and find it can work collaboratively with the idea of entropy regularization.

Continuous Control reinforcement-learning +2

Reinforcement learning with world model

no code implementations30 Aug 2019 Jingbin Liu, Xinyang Gu, Shuai Liu

We propose an agent framework that integrates off-policy reinforcement learning with world model learning, so as to embody the important features of intelligence in our algorithm design.

Decision Making model +3

Cannot find the paper you are looking for? You can Submit a new open access paper.