PPL
Shangtong Zhang
Papers (8)
Latent Q-Barrier Shielding for Safe In-Context Reinforcement LearningPredicting Plasticity in Deep Continual Learning: A Theoretical PerspectiveBeyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement LearningMathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical LibrariesConvergence and Emergence of In-Context Reinforcement Learning with Chain of ThoughtAlmost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau DriftOn the Divergence of Differential Temporal Difference Learning without Local ClocksAdaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning