Labels

Agent-in-the-loop evaluation

Structure of the benchmark

Something isn't working

Task set, fixtures and subsets

Documentation

Improvements or additions to documentation

This issue or pull request already exists

New feature or request

Good for newcomers

Extra attention is needed

This doesn't seem right

Protocol and driver compatibility layer

Web platform semantics layer

Frozen interactive environments layer

End-to-end agent evaluation layer

Licensing and redistribution

Further information is requested

Open question, not yet scheduled

Reinforcement learning environments

Scoring rules and denominators

This will not be worked on