Tianren Zhang

About

Tianren Zhang is a rising researcher in artificial intelligence, with a focus on advancing reinforcement learning (RL) and robot imitation learning. His work tackles critical challenges in scaling RL to complex, real-world tasks, particularly through hierarchical and history-based approaches. Zhang’s most cited paper, “Adjacency Constraint for Efficient Hierarchical Reinforcement Learning” (2022, 31 citations), introduces a novel method to improve training efficiency by constraining the goal space in hierarchical RL, addressing a key bottleneck in the field. He also explores continual learning in robotics with “CRIL: Continual Robot Imitation Learning via Generative and Prediction Model” (2021, 17 citations), enabling robots to acquire diverse skills sequentially from demonstrations—a significant step toward practical, lifelong learning systems. Additionally, his work on data-efficient self-supervised learning from demonstration videos (2021) and fast counterfactual inference for history-based RL (2023) demonstrates a commitment to reducing data requirements and improving decision-making under partial observability. With a growing citation impact, Zhang’s contributions are shaping more efficient, adaptable AI systems for robotics and autonomous agents.

Research Focus

Key Achievements

Top Papers

1. 1
   Adjacency Constraint for Efficient Hierarchical Reinforcement Learning

   31 citations · 2022
2. 2
   CRIL: Continual Robot Imitation Learning via Generative and Prediction Model

   17 citations · 2021
3. 3
   Primitive-contrastive network: data-efficient self-supervised learning from robot demonstration videos

   6 citations · 2021
4. 4
   Fast Counterfactual Inference for History-Based Reinforcement Learning

   3 citations · 2023

Key Collaborators

Contact & Links