JuliaReinforcementLearning / ReinforcementLearningTrajectories.jl

A generalized experience replay buffer for reinforcement learning
MIT License
8 stars 8 forks source link

update EpisodeSamplerRatioController to EpisodesBuffer #52

Open HenriDeh opened 1 year ago

HenriDeh commented 1 year ago

The controller only counts the number of terminal flags to determine the current ratio. It therefore does not work with non-episodic environments. Extending to that case should not be too difficult with the new EpisodesBuffer.