David Roman Halder - Universidade NOVA de Lisboa

Research activity per year

1 Preprint

Using Genetic Programming to Improve Data Collection for Offline Reinforcement Learning
Halder, D. R., Bação, F. & Douzas, G., 8 Oct 2024, (Submitted) Social Science Research Network (SSRN), Elsevier, p. 1-73, 73 p.
Research output: Working paper › Preprint

[Software] Using Genetic Programming to Improve Data Collection for Offline Reinforcement Learning
Halder, D. R. (Creator), GitHub, 17 Jun 2024
https://github.com/dropthedave/offlineRL_thesis and one more link, http://hdl.handle.net/10362/174691 (show fewer)
Dataset