pith. sign in

Shangtong Zhang

Identifiers

  • name variant Shangtong Zhang 0.60 · backfill

Papers (20)

  1. Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning cs.LG · 2026 · author #4
  2. Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning cs.LG · 2026 · author #3
  3. Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective cs.LG · 2026 · author #6
  4. Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning cs.LG · 2026 · author #6
  5. MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries cs.LO · 2026 · author #3
  6. Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought cs.LG · 2026 · author #4
  7. Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift cs.LG · 2026 · author #3
  8. On the Divergence of Differential Temporal Difference Learning without Local Clocks cs.LG · 2026 · author #2
  9. Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning cs.LG · 2026 · author #3
  10. MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics cs.LO · 2026 · author #8
  11. Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning cs.LG · 2025 · author #3
  12. Safe In-Context Reinforcement Learning cs.LG · 2025 · author #7
  13. Reward Is Enough: LLMs Are In-Context Reinforcement Learners cs.LG · 2025 · author #6
  14. GameChat: Multi-LLM Dialogue for Safe, Agile, and Socially Optimal Multi-Agent Navigation in Constrained Environments cs.RO · 2025 · author #2
  15. Distributional Reinforcement Learning for Efficient Exploration cs.LG · 2019 · author #2
  16. ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search cs.LG · 2018 · author #1
  17. QUOTA: The Quantile Option Architecture for Reinforcement Learning cs.LG · 2018 · author #1
  18. A Deeper Look at Experience Replay cs.LG · 2017 · author #1
  19. Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control cs.LG · 2017 · author #1
  20. Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks cs.LG · 2016 · author #2

Mentions

  • 2605.31172 #4 · arxiv_oai · confidence 0.70 Shangtong Zhang
  • 2509.26442 #3 · arxiv_oai · confidence 0.70 Shangtong Zhang
  • 2509.25582 #7 · arxiv_oai · confidence 0.70 Shangtong Zhang
  • 2602.02561 #8 · arxiv_oai · confidence 0.70 Shangtong Zhang
  • 2605.25267 #3 · arxiv_oai · confidence 0.70 Shangtong Zhang
  • 2605.07333 #6 · arxiv_oai · confidence 0.70 Shangtong Zhang

Frequent Coauthors