Ray VS ml-agents

22. Ray | Github | tutorial

Training times for GSM8k are mentioned here: https://github.com/ray-project/ray/tree/master/doc/source/te...

Here's a reference from RLlib that points to docs and an example, and here's one from one of my projects that includes all my own implementations

RLlib

⦿ AWS Glue Data Quality - Automatic data quality rule recommendations based on your data AWS Glue for Ray - Data integration with Ray (ray.io), a popular new open-source compute framework that helps you scale Python workloads

https://ray.io (just dropping the link)

I've wondered whether it's easier to add data analyst stuff to Elixir that Python seems to have, or add features to Python that Erlang (and by extension Elixir) provides out of the box.

By what I can see, if you want multiprocessing on Python in an easier way (let's say running async), you have to use something like ray core[0], then if you want multiple machines you need redis(?). Elixir/Erlang supports this out of the box.

Explorer[1] is an interesting approach, where it uses Rust via Rustler (Elixir library to call Rust code) and uses Polars as its dataframe library. I think Rustler needs to be reworked for this usecase, as it can be slow to return data. I made initial improvements which drastically improves encoding (https://github.com/elixir-nx/explorer/pull/282 and https://github.com/elixir-nx/explorer/pull/286, tldr 20+ seconds down to 3).

[0] https://github.com/ray-project/ray

I am a beginner to using ML Agents to simulate an environment for DL i am trying to trial runs by tinkering through different values between the action space and keep encountering this issue when attempting to run a new trial. I've tried mlagents-learn --force and mlagents-learn --run-id=newtest but both prompt the same error message. Using linux, I am aware of a similar bug occuring in older versions (https://github.com/Unity-Technologies/ml-agents/issues/1505) but solutions didn't fix it.

The Github page for ML-Agents has a fairly straight forward example.

Very few commits in the last year and not many new features (https://github.com/Unity-Technologies/ml-agents/commits/develop)

and PR content: https://github.com/Unity-Technologies/ml-agents/commit/ed212103e451449bf84711a4a8f7bf11dfb1211a

Unity can build a stand-alone application or be used as a library. Javascript is deprecated, and Boo along with it although it was never really supported to begin with. Various types of machine learning are supported through the ML-Agent Toolkit and pretty well documented. The toolkit has a Python API but you should be careful about doing anything too unusual in Unity because the documentation tends to have a lot of dead-ends.

Op, I'd just pull the repo again to a new folder from https://github.com/Unity-Technologies/ml-agents (use SourceTree for simplicity if you don't know git).

My github issue on their documentation: https://github.com/Unity-Technologies/ml-agents/issues/5899