Data-efficient pipeline for offline reinforcement learning with limited data
A Nie, Y Flet-Berliac, D Jordan… - Advances in …, 2022 - proceedings.neurips.cc
Offline reinforcement learning (RL) can be used to improve future performance by
leveraging historical data. There exist many different algorithms for offline RL, and it is well …
leveraging historical data. There exist many different algorithms for offline RL, and it is well …
[PDF][PDF] A Study on Designing a Deep Reinforcement Learning Library towards Practical Applications
T Seno - 2023 - koara.lib.keio.ac.jp
Deep reinforcement learning (RL) has shown significant advancements in various domains.
Building a reusable library is essential to accelerate the research and development process …
Building a reusable library is essential to accelerate the research and development process …