Weight Initialization for SAC Discrete

p-christ / Deep-Reinforcement-Learning-Algorithms-with-PyTorch

PyTorch implementations of deep reinforcement learning algorithms and environments

MIT License

5.59k stars 1.19k forks source link

Weight Initialization for SAC Discrete #53

Open nageshky97s opened 4 years ago

nageshky97s commented 4 years ago

In your paper https://arxiv.org/pdf/1910.07207.pdf, the hyperparameter section states that you have used He weight initialization for the networks, but you seem to be using Xavier initialization for the Actor Critic in SAC discrete.