From e3db7a27e6cc08d255ba24b11df4d1f76b5f578d Mon Sep 17 00:00:00 2001 From: Ming Zhu Date: Mon, 11 Apr 2022 21:09:54 +0800 Subject: [PATCH] Update agents.rst --- docs/source/architecture/three_layer/agents.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/architecture/three_layer/agents.rst b/docs/source/architecture/three_layer/agents.rst index f2c4a7d00..8eeae30db 100644 --- a/docs/source/architecture/three_layer/agents.rst +++ b/docs/source/architecture/three_layer/agents.rst @@ -5,7 +5,7 @@ DRL agents are built by fine-tuned standard DRL algorithms depending on three famous DRL library: ElegantRL, Stable Baseline 3, and RLlib. -Supported algorithms includes: DQN, DDPG, Multi-Agent DDPG, PPO, SAC, A2C and TD3. We also allow users to design their own DRL algorithms by adapting these DRL algorithms, e.g., Adaptive DDPG, or employing ensemble methods. The comparison of DRL algorithms is shown in the table bellow: +The supported algorithms include: DQN, DDPG, Multi-Agent DDPG, PPO, SAC, A2C and TD3. We also allow users to design their own DRL algorithms by adapting these DRL algorithms, e.g., Adaptive DDPG, or employing ensemble methods. The comparison of DRL algorithms is shown in the table bellow: .. image:: ../../image/alg_compare.png :align: center