Get started
Author

Yuda Song

Observed name: Song, Yuda
ORCID: 0000-0002-1911-4409
Observed ORCID: 0000-0002-1911-4409
OpenAlex ID: A5102963429
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
2022 · Song, Yuda, Zhou, Yifei, et al. · arXiv (Cornell University) · 7
PDF
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
2024 · Song, Yuda, Zhang, Hanlin, et al. · arXiv (Cornell University) · 5
PDF
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
2021 · Yuan, Ye, Song, Yuda, et al. · arXiv (Cornell University) · 5
PDF
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
2021 · Song, Yuda, Sun, Wen · arXiv (Cornell University) · 5
PDF
Provable Benefits of Representational Transfer in Reinforcement Learning
2022 · Agarwal, Alekh, Song, Yuda, et al. · arXiv (Cornell University) · 2
PDF
Provably Efficient Model-based Policy Adaptation
2020 · Song, Yuda, Mavalankar, Aditi, et al. · arXiv (Cornell University) · 2
PDF
The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
2024 · Yuda Song, Gokul Swamy, et al. · neural information processing systems · 1
PDF
Harness Learning Enables Generalizable Test-Time Adaptation
2026 · Zhang, Alvin, Liu, Xuecheng, et al. · arXiv (Cornell University)
PDF
Tail-Likelihood Reinforcement Learning
2026 · Ramasubramanian, Shrinivas, Arora, Daman, et al. · arXiv (Cornell University)
PDF
Expanding the Capabilities of Reinforcement Learning via Text Feedback
2026 · Song, Yuda, Chen, Lili, et al. · arXiv (Cornell University)
PDF
Maximum Likelihood Reinforcement Learning
2026 · Tajwar, Fahim, Zeng, Guanning, et al. · arXiv (Cornell University)
PDF
To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning
2025 · Song, Yuda, Rohatgi, Dhruv, et al. · arXiv (Cornell University)
PDF
To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
2025 · Yuda Song, Dhruv Rohatgi, et al. · neural information processing systems
Hybrid Reinforcement Learning from Offline Observation Alone
2024 · Song, Yuda, Bagnell, J. Andrew, et al. · arXiv (Cornell University)
PDF
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
2024 · Song, Yuda, Wu, Lili, et al. · arXiv (Cornell University)
PDF
SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
2024 · Song, Yuda, Sun, Zehao, et al. · arXiv (Cornell University)
PDF
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
2023 · Zhou, Yifei, Sekhari, Ayush, et al. · arXiv (Cornell University)
PDF
The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
2023 · Vemula, Anirudh, Song, Yuda, et al. · arXiv (Cornell University)
PDF
Representation Learning for General-sum Low-rank Markov Games
2022 · Ni, Chengzhuo, Song, Yuda, et al. · arXiv (Cornell University)
PDF
Online No-regret Model-Based Meta RL for Personalized Navigation
2022 · Song, Yuda, Yuan, Ye, et al. · arXiv (Cornell University)
PDF
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach
2022 · Zhang, Xuezhou, Song, Yuda, et al. · arXiv (Cornell University)
PDF
Works count: 21
Citation count: 27
H-index: 4
I10-index:
Year
Topic
Type