Author

Perry Dong

Observed name: Dong, Perry

Institution: Stanford University

Observed institutions: University of California, Berkeley, Stanford University

OpenAlex ID: A5113246490

EXPO: Stable Reinforcement Learning with Expressive Policies

2025 · Dong, Perry, Li, Qiyang, et al. · arXiv (Cornell University) · 38

PDF

RLIF: Interactive Imitation Learning as Reinforcement Learning

2023 · Luo, Jianlan, Dong, Perry, et al. · arXiv (Cornell University) · 27

PDF

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models

2026 · Dong, Perry, Hung, Kuo-Han, et al. · arXiv (Cornell University) · 18

PDF

Value Flows

2025 · Dong, Perry, Zheng, Chongyi, et al. · arXiv (Cornell University) · 14

PDF

Reinforcement Learning via Implicit Imitation Guidance

2025 · Dong, Perry, Lessing, Alec M., et al. · arXiv (Cornell University) · 9

PDF

Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning

2023 · Luo, Jianlan, Dong, Perry, et al. · arXiv (Cornell University) · 9

PDF

TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse

2026 · Dong, Perry, Hung, Kuo-Han, et al. · arXiv (Cornell University) · 6

PDF

Reinforcement Learning for Real-Time Vision-Language-Action Policies

2026 · Dong, Perry, Hung, Kuo-Han, et al. · arXiv (Cornell University) · 5

PDF

Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?

2026 · Dong, Perry, Polonsky, Ron, et al. · arXiv (Cornell University) · 4

PDF

FASTER: Value-Guided Sampling for Fast RL

2026 · Dong, Perry, Swerdlow, Alexander, et al. · arXiv (Cornell University) · 4

PDF

Q-Learning With World Models

2026 · Dong, Perry, Jia, Yueru, et al. · arXiv (Cornell University) · 1

PDF

Generative Value Classifier

2026 · Swerdlow, Alexander, Dong, Perry, et al. · arXiv (Cornell University)

PDF

Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning

2026 · Ankile, Lars, Dong, Perry, et al. · arXiv (Cornell University)

PDF

Adaptively Learning to Select-Rank in Online Platforms

2024 · Wang, Jingyuan, Dong, Perry, et al. · arXiv (Cornell University)

PDF

Society of Agents: Regret Bounds of Concurrent Thompson Sampling

2022 · Yan Chen, Perry Dong, et al. · neural information processing systems

Works count: 16

Citation count: 145

H-index: 7

I10-index: 5