Niven Achenjang

As a bare minimum for thinking a new RL algorithm was possible implemented correctly, it is given a [test](https://github.com/NivenT/REnforce/blob/master/tests/bandit.rs) on the [N-armed bandit](https://www.wikiwand.com/en/Multi-armed_bandit) problem. This environment is about as simple...

I guess first off, ideally there would be an [example](https://github.com/NivenT/REnforce/tree/master/examples) for every training algorithm added. For now, the best way I've found to set these up seems to be to...

How I currently envision this working is by making a custom error type, and then having most user-facing functions return `Result`s. I like how [rusty-machine](https://github.com/AtheMathmo/rusty-machine) has their [error type](https://github.com/AtheMathmo/rusty-machine/blob/master/src/learning/error.rs#L13) set...

Basically what the title says; there needs to be more documenting of the code. Everything is required to have some documentation or the compiler will yell at you, but the...

Update Rust Client

2

I updated the rust client to use [reqwest](https://github.com/seanmonstar/reqwest) instead of directly using hyper, fixed a bug in the way box spaces were being sample, and just all around made the...