Gymnasium already contains a large collection of wrappers, but we believe that the wrappers can be improved to
Support arbitrarily complex observation / action spaces. As RL has advanced, action and observation spaces are becoming more complex and the current wrappers were not implemented with these spaces in mind.
Support for numpy, jax and pytorch data. With hardware accelerated environments, i.e. Brax, written in Jax and similar pytorch based programs, numpy is not the only game in town anymore. Therefore, these upgrades will use Jumpy for calling numpy, jax and torch depending on the data.
More wrappers. Projects like Supersuit aimed to bring more wrappers for RL however wrappers can be moved into Gymnasium.
Versioning. Like environments, the implementation details of wrapper can cause changes agent performance. Therefore, we propose adding version numbers with all wrappers.
In v28, we aim to rewrite the VectorEnv to not inherit from Env, as a result new vectorised versions of the wrappers will be provided.
Proposal
Gymnasium already contains a large collection of wrappers, but we believe that the wrappers can be improved to
VectorEnv
to not inherit fromEnv
, as a result new vectorised versions of the wrappers will be provided.Motivation
No response
Pitch
Lambda Observation Wrappers -
wrappers.lambda_observation
Lambda Action Wrappers -
wrappers.lambda_action
Lambda Reward Wrappers -
wrappers.lambda_reward
Common Wrappers -
wrappers.common
Vector Only Wrappers -
vector.wrappers.common
Alternatives
No response
Additional context
No response
Checklist