KR
Keith W. Ross
cs.LGcs.AIstat.MLcs.CLcs.ROcs.SIcs.SYeess.SYcs.CRcs.CV
On Valency
published · living versionsW_eabeejg3·v1 · currentpublished
PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning
with Yuhan Liu, Xinqi Liu, Zixuan Dong, Shenji Wan
1 version
Preprints & journals
28 papers in the corpus · 2008–2026Counting with Attention and LayerNorm: Norm Scaling and Representation Geometry2610.16653v1 · Ayyub Shaffy, Manoj Dhakal, Safal Shrestha et al.2026 · 0 citationsarXiv
Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension2510.01105v2 · George Andriopoulos, Zixuan Dong, Bimarsha Adhikari et al.2025 · 0 citationsarXiv
Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?2507.10174v1 · Yumi Omori, Zixuan Dong, Keith Ross2025 · 0 citationsarXiv
Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training2506.22638v2 · Aadim Nepal, Safal Shrestha, Anubhav Shrestha et al.2025 · 0 citationsarXiv
Minimal Ingredients for Reward Assignment from Expert Demonstrations2506.06793v2 · Zixuan Dong, Yumi Omori, Keith Ross2025 · 0 citationsarXiv
Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning2505.14216v2 · Minwu Kim, Anubhav Shrestha, Safal Shrestha et al.2025 · 0 citationsarXiv
Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings2505.13718v3 · Safal Shrestha, Minwu Kim, Aadim Nepal et al.2025 · 0 citationsProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)
Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model2505.09308v2 · George Andriopoulos, Soyuj Jung Basnet, Juan Guevara et al.2025 · 0 citationsarXiv
Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges2502.08680v1 · Safal Shrestha, Minwu Kim, Keith Ross2025 · 1 citationarXiv
Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning2410.02994v1 · Suei-Wen Chen, Keith Ross, Pierre Youssef2024 · 0 citationsarXiv
The Prevalence of Neural Collapse in Neural Multivariate Regression2409.04180v2 · George Andriopoulos, Zixuan Dong, Li Guo et al.2024 · 2 citationsPublished in 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Cross Entropy versus Label Smoothing: A Neural Collapse Perspective2402.03979v3 · Li Guo, George Andriopoulos, Zifan Zhao et al.2024 · 3 citationsPublished in Transactions on Machine Learning Research(05/2025)
Pre-training with Synthetic Data Helps Offline Reinforcement Learning2310.00771v4 · Zecheng Wang, Che Wang, Zixuan Dong et al.2023 · 1 citationarXiv
On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs2209.02864v2 · Zixuan Dong, Che Wang, Keith Ross2022 · 1 citationarXiv
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning2202.10324v3 · Che Wang, Xufang Luo, Keith Ross et al.2022 · 11 citationsarXiv
Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance2111.09159v3 · Yanqiu Wu, Xinyue Chen, Che Wang et al.2021 · 3 citationsarXiv
On-Policy Deep Reinforcement Learning for the Average-Reward Criterion2106.07329v1 · Yiming Zhang, Keith W. Ross2021 · 20 citationsarXiv
Randomized Ensembled Double Q-Learning: Learning Fast Without a Model2101.05982v2 · Xinyue Chen, Che Wang, Zijian Zhou et al.2021 · 92 citationsarXiv
First Order Constrained Optimization in Policy Space2002.06506v2 · Yiming Zhang, Quan Vuong, Keith W. Ross2020 · 80 citationsarXiv
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning1910.12179v4 · Xinyue Chen, Zijian Zhou, Zheng Wang et al.2019 · 48 citationsarXiv
Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling1910.02208v4 · Che Wang, Yanqiu Wu, Quan Vuong et al.2019 · 20 citationsarXiv
Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past1906.04009v1 · Che Wang, Keith Ross2019 · 41 citationsarXiv
Efficient Entropy for Policy Gradient with Multidimensional Action Space1806.00589v1 · Yiming Zhang, Quan Ho Vuong, Kenny Song et al.2018 · 9 citationsarXiv
Supervised Policy Update for Deep Reinforcement Learning1805.11706v4 · Quan Vuong, Yiming Zhang, Keith W. Ross2018 · 14 citationsarXiv
Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks1709.06916v2 · Haizhong Zheng, Minhui Xue, Hao Lu et al.2017 · 61 citationsarXiv
Mining Anonymity: Identifying Sensitive Accounts on Twitter1702.00164v1 · Sai Teja Peddinti, Keith W. Ross, Justin Cappos2017 · 6 citationsarXiv
I Know Where You are and What You are Sharing: Exploiting P2P Communications to Invade Users' Privacy1109.4039v3 · Stevens Le Blond, Zhang Chao (NYU-Poly), Arnaud Legout et al.2011 · 5 citationsarXiv
Characterizing Video Responses in Social Networks0804.4865v1 · Fabricio Benevenuto, Fernando Duarte, Tiago Rodrigues et al.2008 · 3 citationsarXiv
Career total: 255 works. 28 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.