YP
Yangchen Pan
cs.LGcs.AIstat.MLcs.CVcs.CLcs.CRcs.MAmath.OC
On Valency
published · living versionsW_va2zqy3n·v1 · currentpublished
Learning Dynamics of On-Policy Distillation
with Guan Zhe Hong, Sumeet Ramesh Motwani, Liang Chen, Junchi Yu +3
1 version
Preprints & journals
31 papers in the corpus · 2015–2026Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning2606.27095v1 · Augustinas Jucas, Yangchen Pan2026 · 0 citationsarXiv
Temporal Difference Learning for Diffusion Models2606.15048v1 · Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu et al.2026 · 0 citationsarXiv
NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics2606.15015v2 · Qizhen Ying, Guangming Wang, Yangchen Pan et al.2026 · 0 citationsarXiv
Gradient Residual Connections2602.09190v1 · Yangchen Pan, Qizhen Ying, Philip Torr et al.2026 · 0 citationsarXiv
Measures of Variability for Risk-averse Policy Gradient2504.11412v1 · Yudong Luo, Yangchen Pan, Jiaqi Tan et al.2025 · 0 citationsarXiv
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling2502.01925v2 · Avery Ma, Yangchen Pan, Amir-massoud Farahmand2025 · 0 citationsarXiv
Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination2405.18556v2 · Zhiyao Luo, Yangchen Pan, Peter Watkinson et al.2024 · 0 citationsarXiv
DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime2405.18610v1 · Zhiyao Luo, Mingcheng Zhu, Fenglin Liu et al.2024 · 2 citationsarXiv
An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models2404.15518v4 · Yangchen Pan, Junfeng Wen, Chenjun Xiao et al.2024 · 0 citationsarXiv
A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization2403.11062v3 · Yudong Luo, Yangchen Pan, Han Wang et al.2024 · 0 citationsarXiv
Improving Adversarial Transferability via Model Alignment2311.18495v2 · Avery Ma, Amir-massoud Farahmand, Yangchen Pan et al.2023 · 4 citationsarXiv
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods2308.06703v2 · Avery Ma, Yangchen Pan, Amir-massoud Farahmand2023 · 2 citationsarXiv
An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient2307.08873v3 · Yudong Luo, Guiliang Liu, Pascal Poupart et al.2023 · 3 citationsarXiv
Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning2303.09032v2 · Xutong Zhao, Yangchen Pan, Chenjun Xiao et al.2023 · 3 citationsarXiv
The In-Sample Softmax for Offline Reinforcement Learning2302.14372v2 · Chenjun Xiao, Han Wang, Yangchen Pan et al.2023 · 5 citationsarXiv
Label Alignment Regularization for Distribution Shift2211.14960v5 · Ehsan Imani, Guojun Zhang, Runjia Li et al.2022 · 0 citationsarXiv
Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation2205.10868v5 · Qingfeng Lan, Yangchen Pan, Jun Luo et al.2022 · 4 citationsarXiv
STOPS: Short-Term-based Volatility-controlled Policy Search and its Global Convergence2201.09857v5 · Liangliang Xu, Daoming Lyu, Yangchen Pan et al.2022 · 0 citationsarXiv
An Alternate Policy Gradient Estimator for Softmax Policies2112.11622v2 · Shivam Garg, Samuele Tosatto, Yangchen Pan et al.2021 · 0 citationsarXiv
Understanding and Mitigating the Limitations of Prioritized Experience Replay2007.09569v3 · Yangchen Pan, Jincheng Mei, Amir-massoud Farahmand et al.2020 · 6 citationsarXiv
Maxmin Q-learning: Controlling the Estimation Bias of Q-learning2002.06487v2 · Qingfeng Lan, Yangchen Pan, Alona Fyshe et al.2020 · 107 citationsarXiv
Frequency-based Search-control in Dyna2002.05822v1 · Yangchen Pan, Jincheng Mei, Amir-massoud Farahmand2020 · 7 citationsarXiv
An implicit function learning approach for parametric modal regression2002.06195v2 · Yangchen Pan, Ehsan Imani, Martha White et al.2020 · 4 citationsarXiv
Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online1911.08068v3 · Yangchen Pan, Kirby Banman, Martha White2019 · 7 citationsarXiv
Hill Climbing on Value Estimates for Search-control in Dyna1906.07791v3 · Yangchen Pan, Hengshuai Yao, Amir-massoud Farahmand et al.2019 · 8 citationsarXiv
Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement1810.09103v4 · Samuel Neumann, Sungsu Lim, Ajin Joseph et al.2018 · 2 citationsarXiv
Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control1806.06931v1 · Yangchen Pan, Amir-massoud Farahmand, Martha White et al.2018 · 9 citationsarXiv
Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains1806.04624v1 · Yangchen Pan, Muhammad Zaheer, Adam White et al.2018 · 33 citationsarXiv
Effective sketching methods for value function approximation1708.01298v1 · Yangchen Pan, Erfan Sadeqi Azer, Martha White2017 · 5 citationsarXiv
Accelerated Gradient Temporal Difference Learning1611.09328v2 · Yangchen Pan, Adam White, Martha White2016 · 22 citationsarXiv
Incremental Truncated LSTD1511.08495v3 · Clement Gehring, Yangchen Pan, Martha White2015 · 4 citationsarXiv
Career total: 42 works. 31 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.