RLE-Foundation / RLeXplore

RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven exploration (RIDE).
https://docs.rllte.dev/
MIT License
362 stars 16 forks source link

OffPolicyAlgorithm and obs dict #15

Open hpugq opened 7 months ago

hpugq commented 7 months ago

Is the OffPolicyAlgorithm now supported, as well as the observation space supported as dict?

yuanmingqi commented 7 months ago

yes, OffPolicyAlgorithm is supported. for dict observation space, pls refer to this issue https://github.com/RLE-Foundation/rllte/issues/44#issuecomment-1977575481