The model implementation does not match the description in the paper

chenhongge / SA_DQN

[NeurIPS 2020, Spotlight] State-Adversarial DQN (SA-DQN) for robust deep reinforcement learning

https://arxiv.org/pdf/2003.08938.pdf

31 stars 11 forks source link

The model implementation does not match the description in the paper #2

Open lucifer2859 opened 1 year ago

lucifer2859 commented 1 year ago

The paper mentions ‘We implement Double DQN [72] and Prioritized Experience Replay [58] on four Atari games’, but the actual code implementation does not implement Double DQN, but rather Dueling DQN. So I want to know if there was an error in the description in the paper.