Calarina Muslimani

2 accepted papers

2026

Reward Learning through Ranking Mean Squared Error

Chaitanya Kharyal, Calarina Muslimani, Matthew Taylor

ICML 2026poster

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified. Recent work has proposed learning reward functions from hum…

Cited by 0 Source ↗Scholar ↗

2025

Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning

Calarina Muslimani, Matthew E. Taylor

ICLR 2025poster

To create useful reinforcement learning (RL) agents, step zero is to design a suitable reward function that captures the nuances of the task. However, reward engineering can be a difficult and time-consuming process. Instead, human-in-the-loop RL methods hold the promise of learning reward functio…

Cited by 4 Source ↗PDF ↗Scholar ↗