Jun Tian

No hurry 😃 We can split the implementation into the following steps. ## 1. Implement a recurrent trajectory All the trajectories we have are transition based. We need to create...

That's good idea. However when the buffer is fully filled, we have to maintain the starting index of each episode: decreasing each one and ejecting elements with a negative value....

Still no progress yet. We also need to change the trajectory part.

@JuliaRegistrator register

@JuliaRegistrator register subdir=src/ReinforcementLearningBase

@JuliaRegistrator register subdir=src/ReinforcementLearningEnvironments

@JuliaRegistrator register subdir=src/ReinforcementLearningCore

I can't reproduce this error. Could you switch to a fresh new environment with `] activate --temp` and try again? If you still get the error, more detailed information would...

Ok, confirmed that you are using the latest version and it's just the same one as mine. But I really can't reproduce it... I'll try again on another machine later.

Well, I tried again on a Windows and a Ubuntu machine, and I still can't reproduce it. But based on the error message, it seems the `ReinforcementLearningExperiments` package is not...