Call for Contributions

Reinforcement learning has undergone tremendous progress in recent years. The growing number of algorithms begets the need for comprehensive tools and implementations. Thus we call for all kinds of contributions from the community, including bug reports, feature proposals and implementations of new algorithms or reinforcement learning environments. This page is used to track what we hope to be added in the next few years.

Environments

Many reinforcement learning environments in the Python world are not available in Julia yet. Though we can leverage PyCall.jl to interact with them, the overheads usually make this approach unacceptable. Following are some experiments we'd like to have, either by wrapping the underlying C/C++ libraries or rewriting in Julia from scratch.

Beside writing environments, it would be great if a unified wrapper is also provided in ReinforcementLearningEnvironments.jl.

Algorithms

Note that each algorithm is suggested to provide at least one reproducible experiment.

Policy Gradient

Model Based

Counterfactual Regret

Infrastructures

Visualization

Distributed Computing

Other Backends

Corrections

If you see mistakes or want to suggest changes, please create an issue on the source repository.