PPL
Zixuan Xie
Papers (6)
From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor DiscoveryOffline Two-Player Zero-Sum Markov Games with KL RegularizationBeyond 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 Drift