Reinforcement Learning

An information-theoretic analysis explaining why policy gradient learns 1 bit per episode and why LoRA works for RL fine-tuning.

We prove HyperAgent closes a theoretical gap in scalable exploration. Further, GPT-HyperAgent addresses risk and efficiency challenges in human-Al interplay for automated content moderation with human feedback.

Addressing data and computation efficiency challenges in real-world deployments of RL Agents. It achieves significant efficiency gains in deep RL benchmarks as well as theoretical milestones.

Has implications on how the integration of prior knowledge enhances the efficiency of RL agents without extensive online exploration.

Practically and provably efficient RL under resource constraints!

Game-theoretic decision-making in multi-agent systems. I developed optimistic TS type algorithm that significantly reduce experimental costs in applications such as traffic management and radar communications.

Practically and provably efficient RL under resource constraints!

Addressing efficiency chanllenge in RL by HyperFQI algorithm