diff --git a/papers/Policy_gradient/PDF/A Distributional Perspective on Reinforcement Learning.pdf b/papers/Policy_gradient/PDF/A Distributional Perspective on Reinforcement Learning.pdf
new file mode 100644
index 0000000..8275564
Binary files /dev/null and b/papers/Policy_gradient/PDF/A Distributional Perspective on Reinforcement Learning.pdf differ
diff --git a/papers/Policy_gradient/PDF/High-Dimensional Continuous Control Using Generalised Advantage Estimation.pdf b/papers/Policy_gradient/PDF/High-Dimensional Continuous Control Using Generalised Advantage Estimation.pdf
new file mode 100644
index 0000000..82e05e6
Binary files /dev/null and b/papers/Policy_gradient/PDF/High-Dimensional Continuous Control Using Generalised Advantage Estimation.pdf differ
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..c0536cd
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