Ting Qiao[RL]Soft-RL: Maximum Entropy Reinforcement Learning as Probabilistic InferenceThe first book you read about Reinforcement Learning is likely the book Reinforcement Learning: An Introduction. In the book, dear Richard…Sep 27, 2021Sep 27, 2021
Ting QiaoPILCO explanationPILCO is one of the most important Model-Based Reinforcement Learning algorithms draws a lot of attention from researchers. It is using…Sep 5, 20205Sep 5, 20205
![[RL]Soft-RL: Maximum Entropy Reinforcement Learning as Probabilistic Inference](https://miro.medium.com/v2/resize:fill:160:106/1*kdtlh-kvxcIeIaSbyczX9Q.png)
![[RL]Soft-RL: Maximum Entropy Reinforcement Learning as Probabilistic Inference](https://miro.medium.com/v2/resize:fill:320:214/1*kdtlh-kvxcIeIaSbyczX9Q.png)
