diff --git a/papers/Policy_gradient/PDF/Scalable trust-region method for deep reinforcement learning using Kronecker-factored.pdf b/papers/Policy_gradient/PDF/Scalable trust-region method for deep reinforcement learning using Kronecker-factored.pdf
new file mode 100644
index 0000000..5c64194
Binary files /dev/null and b/papers/Policy_gradient/PDF/Scalable trust-region method for deep reinforcement learning using Kronecker-factored.pdf differ
diff --git a/papers/Policy_gradient/PDF/Trust Region Policy Optimization.pdf b/papers/Policy_gradient/PDF/Trust Region Policy Optimization.pdf
new file mode 100644
index 0000000..9fd80cf
Binary files /dev/null and b/papers/Policy_gradient/PDF/Trust Region Policy Optimization.pdf differ