Meta-Reinforcement Learning in Non-Stationary and Dynamic Environments
The code of CEMRL is released at https://github.com/BZSROCKETS/cemrl .
All experiments (newly added videos are at the bottom of this page)
![](https://www.google.com/images/icons/product/drive-32.png)
Single experiments
Single experiments
Stationary, Parametric Environments
![](https://www.google.com/images/icons/product/drive-32.png)
Half-Cheetah stationary direction
![](https://www.google.com/images/icons/product/drive-32.png)
Half-Cheetah stationary velocity
Non-Stationary, Parametric Environments
![](https://www.google.com/images/icons/product/drive-32.png)
Half-Cheetah non-stationary direction
![](https://www.google.com/images/icons/product/drive-32.png)
Half-Cheetah non-stationary velocity
![](https://www.google.com/images/icons/product/drive-32.png)
Ant non-stationary direction
![](https://www.google.com/images/icons/product/drive-32.png)
Ant non-stationary velocity
Continual Learning
![](https://www.google.com/images/icons/product/drive-32.png)
Half-Cheetah continual learning
Stationary, Non-Parametric Environments
![](https://www.google.com/images/icons/product/drive-32.png)
Half-Cheetah mixed tasks
Supplement Videos (Hopper and Walker)
![](https://www.google.com/images/icons/product/drive-32.png)
![](https://www.google.com/images/icons/product/drive-32.png)