Best of luck to you in monetizing your efforts, hope this good publicity will help your cause. Thank you very much for opensourcing reference implementations of state-of-the art reinforcement learning algorithms.<p>One thing that would make playing with this tech more interesting to me and other newcomers is a guide on how to create a new environment for gym or universe, sort of a crash course on what steps need to be made in order to apply your algorithms to my existing problems
I'm currently working on an RL project based on an OpenAI Gym environment and have been reviewing the different frameworks available. So far I’ve come across:<p>- OpenAI Baselines (more a collection of algorithms than a framework)<p>- Keras-RL (looked ideal but has been abandoned)<p>- Tensorflow Agents (An 'official'? Tensorflow library, but very basic- only one algo at present)<p>- rllab (Developed by OpenAI people but seems to be abandoned)<p>- OpenAI Lab (?)<p>- TensorForce<p>My main concerns are: 1. Soundness of the algo implementations. 2. Modularity, ease-of-use, compatibility.<p>I first looked at Baselines as it seemed to best address the first concern but ran into frustrations when for example the DeepQ implementation didn’t work if my Gym’s action_space was a Tuple space. I am working with a team unfamiliar with RL so want something that is as plug-n-play as possible, like Keras. So far TensorForce looks promising. Can anyone add anything more? Thanks