Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Danisa, Siphelele"'
Autor:
Danisa, Siphelele
In this work we investigate the convergence of multiagent soft Q-learning in continuous games where learning is most likely to be affected by relative overgeneralisation. While this will occur more often in multiagent independent learner problems, it
Externí odkaz:
http://hdl.handle.net/11427/37110
https://open.uct.ac.za/bitstream/11427/37110/1/thesis_sci_2022_danisa%20siphelele.pdf
https://open.uct.ac.za/bitstream/11427/37110/1/thesis_sci_2022_danisa%20siphelele.pdf
Autor:
Danisa, Siphelele
In this work we investigate the convergence of multiagent soft Q-learning in continuous games where learning is most likely to be affected by relative overgeneralisation. While this will occur more often in multiagent independent learner problems, it
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3158::364467a54ee67a7e74a7a61752c037d5
http://hdl.handle.net/11427/37110
http://hdl.handle.net/11427/37110
Autor:
Pretorius, Arnu, Tessera, Kale-ab, Smit, Andries P., Formanek, Claude, Grimbly, St John, Eloff, Kevin, Danisa, Siphelele, Francis, Lawrence, Shock, Jonathan, Kamper, Herman, Brink, Willie, Engelbrecht, Herman, Laterre, Alexandre, Beguir, Karim
Breakthrough advances in reinforcement learning (RL) research have led to a surge in the development and application of RL. To support the field and its rapid growth, several frameworks have emerged that aim to help the community more easily build ef
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::afa8821ca6b69018bff1f0f861cffde1