## List of Tables

Chapter 2. Modeling reinforcement learning problems: Markov decision processes

Table 2.1. Example of the side-by-side mathematics and pseudocode we use in this book

Table 2.2. The expected reward calculation in math and pseudocode

Table 2.3. Computing the best action, given the expected rewards

Table 2.4. The softmax equation

Table 2.5. The policy function

Chapter 3. Predicting the best states and actions: Deep Q-networks

Chapter 7. Distributional DQN: Getting the full story

Table 7.1. Frequentist versus Bayesian probabilities

Table 7.2. Computing an expected value from a probability distribution

Table 7.3. Common probability distributions

Table 7.4. The likelihood ratio in math and Python

Table 7.5. The log-likelihood ratio in math and Python

Table 7.6. The weighted log-likelihood ratio in math and Python

Chapter 8. Curiosity-driven exploration