TD(0)-Replay: An Efficient Model-Free Planning with full Replay

Altahhan, A (2018) TD(0)-Replay: An Efficient Model-Free Planning with full Replay. In: International Joint Conference on Neural Networks, 08 July 2018 - 13 July 2018, Brazil. (In Press)

More Information

Divisions: Faculty of Arts, Environment and Technology > Computing and Creative Technologies and Engineering
Status: In Press
Publisher: Institute of Electrical and Electronics Engineers
Uncontrolled Keywords: TD-Replay, Reinforcement Learning, Full Replay,
Depositing User (symplectic) Deposited by Altahhan, Abdulrahman
Date Deposited: 10 Apr 2018 16:04
Last Modified: 10 Apr 2018 16:20
Item Type: Conference or Workshop Item (Paper)

Download

Restricted to Repository staff only.
Due to copyright restrictions, this file is not available for public download. For more information please email openaccess@leedsbeckett.ac.uk.

Export Citation

Share

Statistics

Additional statistics for this record