Soft Actor-Critic for continuous and discrete actions | by Wah Loon Keng | Medium

With the Atari benchmark complete for all the core RL algorithms in SLM Lab, I finally had time to implement a new algorithm, Soft…

Soft Actor-Critic for continuous and discrete actions Wah Loon Keng 4 min read · Aug 11, 2019 -- 4 Listen Share With the Atari benchmark complete for all the core RL algorithms in SLM Lab , I finally had time to implement a new algorithm, Soft Actor-Critic (SAC). This came in two papers: the first which introduces the SAC algorithm https://arxiv.org/abs/1801.01290 the second which improves on it https://arxiv.org/abs/1812.05905 I’ll let you read the papers, which should take just a day to digest, then quickly go through the implementation; the main goal of this post is to show that how it can

saved by

• A P

related reading

• An Updated Introduction to Reinforcement Learning | Sri's Blogsrianumakonda.com
• Soft Actor-Critic - Spinning Up documentationspinningup.openai.com
• The 37 Implementation Details of Proximal Policy Optimization · The ICLR Blog Trackiclr-blog-track.github.io
• Policy Gradient Algorithms | Lil'Loglilianweng.github.io
• A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
• Q-learning is not yet scalableseohong.me
• Part 1: Key Concepts in RL - Spinning Up documentationspinningup.openai.com
• Algorithms — Ray 2.55.1docs.ray.io
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• [1801.01290] Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorarxiv.org
• Deep Q-Networks Explained — LessWronglesswrong.com
• The idea behind Actor-Critics and how A2C and A3C improve them | AI Summertheaisummer.com