Bibliography (7):

1. https://www.lesswrong.com/posts/eoHbneGvqDu25Hasc/rl-with-kl-penalties-is-better-seen-as-bayesian-inference

2. GPT-3: Language Models are Few-Shot Learners

3. Deep reinforcement learning from human preferences

4. Wikipedia Bibliography:

   1. Expected value

   2. Kullback-Leibler divergence

   3. Variational Bayesian methods

   4. Bayesian statistics