Varys, K., Cerutti, F., Sobey, A., & Norman, T. J. (2025). HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning.
Style de citation Chicago (17e éd.)Varys, Kryspin, Federico Cerutti, Adam Sobey, et Timothy J. Norman. HAVA: Hybrid Approach to Value-Alignment Through Reward Weighing for Reinforcement Learning. 2025.
Style de citation MLA (9e éd.)Varys, Kryspin, et al. HAVA: Hybrid Approach to Value-Alignment Through Reward Weighing for Reinforcement Learning. 2025.
Attention : ces citations peuvent ne pas être correctes à 100%.