From e7b7972acf534a9946194bd1c8d774ff2cd6714f Mon Sep 17 00:00:00 2001 From: Yiyuan Yang Date: Sun, 20 Nov 2022 23:36:41 +0800 Subject: [PATCH] Update Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.md --- ...y Deep Reinforcement Learning with a Stochastic Actor.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/papers/Policy_gradient/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.md b/papers/Policy_gradient/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.md index ef3013d..0282de0 100644 --- a/papers/Policy_gradient/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.md +++ b/papers/Policy_gradient/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.md @@ -157,7 +157,11 @@ soft actor-critic算法用伪代码可表示为： 虽然SAC算法采用了energy-based模型，但是实际上策略分布仍为高斯分布，存在一定的局限性。 - +==================================== +作者：杨骏铭 +研究单位：南京邮电大学 +研究方向：强化学习、对抗学习 +联系邮箱：jmingyang@outlook.com