[Feature Request] Continual Learning and Evaluation

[George614]

Hi Danijar,

I've been a big fan of your works. Can you consider adding functionalities for supporting continual reinforcement learning and evaluation setup in the future? I think it's a good direction to go. There are some repositories such as CORA but they focus on model-free RL and they are based off PyTorch. I really appreciate your code style and glad to see you contributing to the field constantly!

Thanks,