451 citations · 1.7k across the 73 of their papers we have counts for
3 papers · 1 filter
Randomized Value Functions via Posterior State-Abstraction Sampling
Dilip Arumugam, Benjamin Van Roy
State abstraction has been an essential tool for dramatically improving the sample efficiency of reinforcement-learning algorithms. Indeed, by exposing and accentuating various typ…
Hypermodels for Exploration
Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi +3
We study the use of hypermodels to represent epistemic uncertainty and guide exploration. This generalizes and extends the use of ensembles to approximate Thompson sampling. The co…
Langevin DQN
Vikranth Dwaracherla, Benjamin Van Roy
Algorithms that tackle deep exploration -- an important challenge in reinforcement learning -- have relied on epistemic uncertainty representation through ensembles or other hyperm…