eager-dev / eagerx

EAGERx is a physics engine abstraction layer for reinforcement learning. EAGERx allows switching between simulators and reality with a single line of code, supports action and observation processing and controller switching for resets.

Home Page:https://eagerx.readthedocs.io/en/master/index.html

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Feature Request] Create another type of BaseEnv that does not require action/observation spaces.

bheijden opened this issue Β· comments

πŸš€ Feature

As of now, all inputs and outputs of an environment require a fully defined Space. However, if we would like to use the environment in settings other than with RL, this requirement might be too strict.

Checklist

  • I have checked that there is no similar issue in the repo (required)