69 citations · 462 across the 66 of their papers we have counts for
3 papers · 2 filters
Dueling Posterior Sampling for Preference-Based Reinforcement Learning
Ellen R. Novoseller, Yibing Wei, Yanan Sui +2
In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing researc…
Control Regularization for Reduced Variance Reinforcement Learning
Richard Cheng, Abhinav Verma, Gabor Orosz +3
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run t…
End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks
Richard Cheng, Gabor Orosz, Richard M. Murray +1
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process…