2 papers
cs.LG2025
RIZE: Adaptive Regularization for Imitation Learning
Adib Karimi, Mohammad Mehdi Ebadzadeh
We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization.…
cs.AI2024
Modified Double DQN: addressing stability
Shervin Halat, Mohammad Mehdi Ebadzadeh, Kiana Amani
Inspired by Double Q-learning algorithm, the Double-DQN (DDQN) algorithm was originally proposed in order to address the overestimation issue in the original DQN algorithm. The DDQ…