search

FluxML / Gym.jl

Gym environments in Julia
MIT License
54 stars 19 forks source link

Standalone implementations of reinforcement learning algorithms #8

Open jean72human opened 5 years ago

jean72human commented 5 years ago

Hello, I would like to know what you think about having some standalone implementations as functions that take in the environment and other parameters and return the trained policy.

Here an example of how this could look like for deep Q learning:

policy = deepq.learn(env, network=q_function_approximator, lr=learning_rate, epsilon=exploration_rate, buffer_size=buffer_size)

I think this would make it easier to quickly get started with deep reinforcement learning with Flux

tejank10 commented 5 years ago

It'd be great to have a sister package, like what baselines is to OpenAI Gym, showing off RL algorithms with Gym.jl

jean72human commented 5 years ago

Should it be a seperate package or can it be included in Gym.jl?

v-i-s-h commented 5 years ago

I'm also really interested to see this happening. Making it a separate package will be useful, I think. Otherwise, users who want to use Gym.jl alone will also have to download the dependencies of this.

Further, which framework you propose will be best suited for this: Knet, Flux or Tensorflow.jl?

tejank10 commented 5 years ago

Making separate package is useful, for the same reasons mentioned by @v-i-s-h . Any of the framework can be used, but I'll be biased towards Flux ;)

jean72human commented 5 years ago

I think Flux would be good for that