diff --git a/papers/Policy_gradient/PDF/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.pdf b/papers/Policy_gradient/PDF/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.pdf
new file mode 100644
index 0000000..15d5180
Binary files /dev/null and b/papers/Policy_gradient/PDF/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.pdf differ