Search Results for author: Tianying Ji

Found 5 papers, 2 papers with code

ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

no code implementations22 Feb 2024 Tianying Ji, Yongyuan Liang, Yan Zeng, Yu Luo, Guowei Xu, Jiawei Guo, Ruijie Zheng, Furong Huang, Fuchun Sun, Huazhe Xu

The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms.

Continuous Control Efficient Exploration

H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps

no code implementations22 Sep 2023 Haoyi Niu, Tianying Ji, Bingqi Liu, Haocheng Zhao, Xiangyu Zhu, Jianying Zheng, Pengfei Huang, Guyue Zhou, Jianming Hu, Xianyuan Zhan

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging.

Offline RL Reinforcement Learning (RL)

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

no code implementations5 Jun 2023 Tianying Ji, Yu Luo, Fuchun Sun, Xianyuan Zhan, Jianwei Zhang, Huazhe Xu

Learning high-quality Q-value functions plays a key role in the success of many modern off-policy deep reinforcement learning (RL) algorithms.

Continuous Control Reinforcement Learning (RL)

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