Akshay Krishnamurthy

5

Papers

69

Total Citations

Papers (5)

Self-Improvement in Language Models: The Sharpening Mechanism

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics

Scalable Online Exploration via Coverability

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics