Create Globally Convergent Offline Reinforcement Learning with Smoothed Bellman Residual Minimization

Create Reasonably reasoning agents can avoid game-theoretic failures in zero-shot, provably.txt

Create LLM Personas as a Substitute for Field Experiments in Method Benchmarking

Rename src/data/MRRC.txt to src/data/Learning NP-Hard Multi-Agent Assignment Planning using GNN_Inference on a Random Graph and Provable Auction-Fitted Q-learning.txt

Rename src/data/Bounded_SC.txt to src/data/Bounded (O(1)) Regret Recommendation Learning via Synthetic Controls Oracle.txt

Upload Is O(log N) practical_Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL.txt

Rename src/data/ERMIRL.txt to src/data/Empirical risk minimization for Inverse RL and Dynamic Discrete Choice models.txt

Upload Stability and Generalization for Bellman Residuals.txt

Rename src/data/BO_language.txt to src/data/Bayesian optimization in language space: An eval-efficient AI self-improvement framework.txt

Rename src/MRRC.txt to src/data/MRRC.txt

Rename src/ERMIRL.txt to src/data/ERMIRL.txt

Rename src/Bounded_SC.txt to src/data/Bounded_SC.txt

Rename src/BO_language.txt to src/data/BO_language.txt