From 77f2f7850169d77c03746fa6a966bf21ec68db3e Mon Sep 17 00:00:00 2001 From: Costa Huang Date: Mon, 21 Mar 2022 16:34:02 -0400 Subject: [PATCH] Fix DDPG docs' description (#139) --- docs/rl-algorithms/ddpg.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/rl-algorithms/ddpg.md b/docs/rl-algorithms/ddpg.md index 0a5721105..da36aa238 100644 --- a/docs/rl-algorithms/ddpg.md +++ b/docs/rl-algorithms/ddpg.md @@ -3,7 +3,7 @@ ## Overview -DDPG is a popular DRL algorithm for continuous control. It runs reasonably fast by leveraging vector (parallel) environments and naturally works well with different action spaces, therefore supporting a variety of games. It also has good sample efficiency compared to algorithms such as DQN. +DDPG is a popular DRL algorithm for continuous control. It extends DQN to work with the continuous action space by introducing a deterministirc actor that directly outputs continuous actions. DDPG also combines techniques from DQN such as thhe replay buffer and target network. Original paper: @@ -13,6 +13,7 @@ Original paper: Reference resources: * :material-github: [sfujim/TD3](https://github.com/sfujim/TD3) +* [Deep Deterministic Policy Gradient | Spinning Up in Deep RL](https://spinningup.openai.com/en/latest/algorithms/ddpg.html) ## Implemented Variants