diff --git a/papers/Policy_gradient/PDF/Action-depedent Control Variates for Policy Optimization via Stein’s Identity.pdf b/papers/Policy_gradient/PDF/Action-depedent Control Variates for Policy Optimization via Stein’s Identity.pdf
new file mode 100644
index 0000000..0f60d39
Binary files /dev/null and b/papers/Policy_gradient/PDF/Action-depedent Control Variates for Policy Optimization via Stein’s Identity.pdf differ
diff --git a/papers/Policy_gradient/PDF/Bridging the Gap Between Value and Policy Based Reinforcement Learning.pdf b/papers/Policy_gradient/PDF/Bridging the Gap Between Value and Policy Based Reinforcement Learning.pdf
new file mode 100644
index 0000000..b2299f2
Binary files /dev/null and b/papers/Policy_gradient/PDF/Bridging the Gap Between Value and Policy Based Reinforcement Learning.pdf differ
diff --git a/papers/Policy_gradient/PDF/The Mirage of Action-Dependent Baselines in Reinforcement Learning.pdf b/papers/Policy_gradient/PDF/The Mirage of Action-Dependent Baselines in Reinforcement Learning.pdf
new file mode 100644
index 0000000..d65fe72
Binary files /dev/null and b/papers/Policy_gradient/PDF/The Mirage of Action-Dependent Baselines in Reinforcement Learning.pdf differ