9 Papers
27 Citations
Te Sun is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 5, co-authored 9 publications.
Chat about Author
Papers
•Proceedings Article
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
René Traoré,Hugo Caselles-Dupré,Timothée Lesort,Te Sun,Natalia Díaz-Rodríguez,David Filliat +5 more
- 05 May 2019
TL;DR: In this article, a 3-wheel omni-directional robot is trained using learned features as input, rather than raw observations, allowing better sample efficiency and allowing the robot to solve all tasks it has encountered without forgetting past tasks.
•Posted Content
Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control.
Ke Lin,Liang Gong,Xudong Li,Te Sun,Binhao Chen,Chengliang Liu,Zhengfeng Zhang,Jian Pu,Junping Zhang +8 more
TL;DR: A sample efficient DRL-EG (DRL with efficient guidance) algorithm, in which a discriminator and a guider G are modeled by a small number of expert demonstrations, which can help the agent to escape from a local optimum.
8
DisCoRL: Continual Reinforcement Learning via Policy Distillation
René Traoré,Hugo Caselles-Dupré,Timothée Lesort,Te Sun,Guanghang Cai,David Filliat,Natalia Díaz-Rodríguez +6 more
- 14 Dec 2019
TL;DR: In this article, the authors propose DisCoRL, an approach combining state representation learning and policy distillation for multi-task reinforcement learning, which can solve all tasks and automatically infer which one to run.
7
RobotDrlSim: A Real Time Robot Simulation Platform for Reinforcement Learning and Human Interactive Demonstration Learning
Te Sun,Liang Gong,Xvdong Li,Shenghan Xie,Zhaorun Chen,Qizi Hu,David Filliat +6 more
- 01 Jan 2021
TL;DR: A standardized API interfacing mechanism for coordinating diverse environments on RobotDrlSim platform, where PyBullet simulator is equipped with an API to form a physical engine for robotics simulation.
5
Demonstration Guided Actor-Critic Deep Reinforcement Learning for Fast Teaching of Robots in Dynamic Environments
Liang Gong,Te Sun,Xudong Li,Ke Lin,Natalia Díaz-Rodríguez,David Filliat,Zhengfeng Zhang,Junping Zhang +7 more
TL;DR: This work proposes a novel demonstration learning framework for actor-critic based RL algorithms that makes full use of the exploration property of the RL algorithm, which is feasible for fast teaching robots in dynamic environments.
3