Enhanced Off-Policy Reinforcement Learning With Focused Experience Replay

Enhanced Off-Policy Reinforcement Learning With Focused Experience Replay

Utilizing the collected experience tuples in the replay buffer (RB) is the primary way of exploiting the experiences in the off-policy reinforcement learning (RL) algorithms, and, therefore, the sampling scheme for the experience tuples in the RB can be critical for experience utilization. In this p...

Full description

Bibliographic Details
Main Authors: Seung-Hyun Kong, I. Made Aswin Nahrendra, Dong-Hee Paek
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Reinforcement learning
off-policy
actor-critic
experience replay
replay buffer
Online Access:https://ieeexplore.ieee.org/document/9444458/

Internet

https://ieeexplore.ieee.org/document/9444458/

Similar Items