Reinforcement Learning and Bandits Lab

PhD Students

• 洪偉 (MS Student during Aug. 2019-Feb. 2021, admitted to PhD program since Feb. 2021)

  • Topic: Deep reinforcement learning for network control

• 洪鈺恆 (MS Student during Aug. 2019-Aug. 2021, admitted to PhD program since Aug. 2021)

  • Topic: Bandit learning

• 連云暄 (co-advised by Prof. Yu-Shuen Wang)

• 何國豪 (co-advised by Prof. I-Chen Wu)

• 王廣達 (co-advised by Prof. Wen-Chih Peng)

MS Students

• 葉佳翰 (BS@ NCTU-CS)

  • Topic: Action-Constrained IL

• 詹昀銘 (BS@ NCTU-CS)

  • Topic: Physical Simulators for RL

• 陳盈圖 (BS@ NCTU-CS)

  • Topic: Multi-Objective RL

• 陳子安 (BS@ NCTU-CS)

  • Topic: Adversarial RL

• 陳明宏 (BS@ NCTU-Applied Math)

  • Topic: Offline-to-Online RL

• 陳騰睿 (BS@ NCCU-Applied Math)

  • Topic: Generative Modeling for RL

• 朱立民 (BS@ NSYSU-Applied Math)

  • Topic: Offline-to-Online Imitation Learning

• 吳秉澍 (BS@ NYCU-CS)

  • Topic: Zero-shot RL

• 楊竣傑 (BS@ NYCU-CS)

  • Topic: Multi-objective RL

• 林禹亨 (BS@ NYCU-CS)

  • Topic: Sequence modeling for RL

• 皮恩亞 (BS@ NCU-Math)

  • Topic: Cross-Domain RL

• 林睿騰 (BS@ NYCU-CS)

  • Topic: Restless bandits

Research Assistants

• 許嘉喻

• 温柏萱

Undergraduate Students

Joining in 2020

• 鍾承佑 (now MS student in CMU)、柯秉志、徐煜倫

• 王耀德、蔡育呈、周俊毅

• 張祐銘、張祐閤

Joining in 2021

• 鄒翔傑 (now MS student in UCSD)、黃迺絜

• 洪婕庭、陳筱霓

• 許承壹、林浩君

Joining in 2022

• 吳文心、温柏萱

• 孟祥蓉、廖兆琪

• 沈克軒 (now MS student in TAMU)、陳秉劼

• 楊竣傑

Joining in 2023

• 吳秉澍、林睿騰

• 王振倫、楊沁瑜、施柏江

• 林佑家

Joining in 2024

• 徐嘉亨

• 黃佑得

Alumni

• 林峻立 (Sept. 2019-Aug. 2021, BS@NCU-CS, now in MediaTek)

  • Thesis: Frank-Wolfe Policy Optimization for Reinforcement Learning with Action Constraints

• 謝秉瑾 (Sept. 2019-Aug. 2021, BS@NCCU-CS, now in Inventec)

  • Thesis: Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization

• 李昕 (Sept. 2019-March. 2022, BS@NCKU-CS, now in PHISON)

  • Thesis: Accelerating Gaussian Process Regression via Meta-Learned Neural Processes: A Utility-Based MAML Approach

• 蘇信恩 (Feb. 2021-Sept. 2022, BS@NCTU-CS, BS+MS in 5 years, now in Google)

  • Thesis: Coordinate Ascent Policy Optimization

• 黃柏愷 (Sept. 2020-Sept. 2022, BS@NCKU-CS, now in Trend Micro Inc.)

  • Thesis: Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots

• 郭俊廷 (Sept. 2020-Oct. 2022, BS@NCTU-EE, now in MediaTek)

  • Thesis: Adaptive-UCB for Online Restless Bandits

• 黃睿宇 (Sept. 2020-Oct. 2022, BS@NCTU-IEM, now in MediaTek)

  • Thesis: Multi-Objective Time-Varying Bayesian Optimization

• 楊上萱 (Sept. 2020-Nov. 2022, BS@NCTU-CS, now in MediaTek)

  • Thesis: Variance-Reduced Frank-Wolfe Policy Optimization for Action-Constrained RL

• 歐陽良雋 (Sept. 2020-Dec. 2022, BS@ NCTU-EE, now in MediaTek)

  • Thesis: Robustifying Proximal Policy Optimization Against Noisy Critics

• 楊祐維 (Sept. 2021-Oct. 2023, BS@ NCTU-CS, now in MediaTek)

  • Thesis: Model Selection for Offline Model-Based RL via Bayesian Optimization

• 吳程畯 (Sept. 2021-Dec. 2023, BS@ NCHU-Applied Math)

  • Thesis: Learning From Expert Demonstrations With Incomplete Observations

• 朱文滔 (Sept. 2021-March. 2024, BS@ NCU-Math)

  • Thesis: Provably Convergent Mixture-of-Experts in Reinforcement Learning

• 陳彥儒 (Sept. 2022-June. 2024, BS@ NCTU-Applied Math, now in Synopsys)

  • Thesis: Accelerated Policy Gradient: On the Convergence Rates of Nesterov's Momentum for Reinforcement Learning

• 張千祐 (Sept. 2022-June. 2024, BS@ NCTU-CS)

  • Thesis: Learning From Demonstrative Experts of Diverse Preference

• 潘冠蓁 (Sept. 2022-July. 2024, BS@ NCTU-CS, now in TSMC)

  • Thesis: Survive on Planet Pandora: Robust Cross-Domain RL Under Distinct State-Action Representations