6 papers
Reward Learning through Ranking Mean Squared Error
Chaitanya Kharyal, Calarina Muslimani, Matthew E. Taylor
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…
The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning
Calarina Muslimani, Yunshu Du, Kenta Kawamoto +3
The success of reinforcement learning (RL) is fundamentally tied to having a reward function that accurately reflects the task objective. Yet, designing reward functions is notorio…
Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners
Calarina Muslimani, Kerrick Johnstonbaugh, Suyog Chandramouli +3
Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a we…
Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity
Calarina Muslimani, Bram Grooten, Deepak Ranganatha Sastry Mamillapalli +3
To integrate into human-centered environments, autonomous agents must learn from and adapt to humans in their native settings. Preference-based reinforcement learning (PbRL) can en…
Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning
Calarina Muslimani, Matthew E. Taylor
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 d…
Reinforcement Teaching
Calarina Muslimani, Alex Lewandowski, Dale Schuurmans +2
Machine learning algorithms learn to solve a task, but are unable to improve their ability to learn. Meta-learning methods learn about machine learning algorithms and improve them…