4 papers · 1 filter
Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
Ke Sun, Yingnan Zhao, Enze Shi +4
The remarkable empirical performance of distributional reinforcement learning (RL) has garnered increasing attention to understanding its theoretical advantages over classical RL.…
Budget-constrained Active Learning to Effectively De-censor Survival Data
Ali Parsaee, Bei Jiang, Zachary Friggstad +1
Standard supervised learners attempt to learn a model from a labeled dataset. Given a small set of labeled instances, and a pool of unlabeled instances, a budgeted learner can use…
Distributional Reinforcement Learning with Regularized Wasserstein Loss
Ke Sun, Yingnan Zhao, Wulong Liu +2
The empirical success of distributional reinforcement learning (RL) highly relies on the choice of distribution divergence equipped with an appropriate distribution representation.…
How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?
Ke Sun, Bei Jiang, Linglong Kong
Distributional reinforcement learning, which focuses on learning the entire return distribution instead of only its expectation in standard RL, has demonstrated remarkable success…