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

no code implementations • 8 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.

Physical Simulations Reinforcement Learning (RL)

Soft Q Network

no code implementations • 20 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 implementations • 2 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 +1

Reinforcement learning with world model

no code implementations • 30 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 reinforcement-learning +1