Search Results for author: Alexey Skrynnik

Found 6 papers, 4 papers with code

Long-Term Exploration in Persistent MDPs

1 code implementation21 Sep 2021 Leonid Ugadiarov, Alexey Skrynnik, Aleksandr I. Panov

Exploration is an essential part of reinforcement learning, which restricts the quality of learned policy.

Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations

1 code implementation17 Jun 2020 Alexey Skrynnik, Aleksey Staroverov, Ermek Aitygulov, Kirill Aksenov, Vasilii Davydov, Aleksandr I. Panov

There are two main approaches to improving the sample efficiency of reinforcement learning methods - using hierarchical methods and expert demonstrations.

Hierarchical Reinforcement Learning reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.