Support CommonRLInterface

[findmyway]

Though all the environments are written based on ReinforcementLearningBase.jl, it's relatively easy to support the minimal interfaces provided in CommonRLInterface.

struct CommonEnvWrapper{T<:RLBase.AbstractEnv} <: CommonRL.AbstractCommonEnv
     env::T
end

convert(CommonRL.AbstractCommonEnv, env::RLBase.AbstractEnv) = CommonEnvWrapper(env)

function CommonRL.step!(env::CommonEnvWrapper, action)
    env.env(action)
    obs = RLBase.observe(env.env)
    RLBase.get_state(obs), RLBase.get_reward(obs), RLBase.get_terminal(obs), obs
end

function CommonRL.reset!(env::CommonEnvWrapper)
    RLBase.reset!(env.env)
    obs = RLBase.observe(env.env)
    RLBase.get_state(obs), RLBase.get_reward(obs), RLBase.get_terminal(obs), obs
end

CommonRL.actions(env::CommonEnvWrapper) = RLBase.get_action_space(env)

What do you think? @zsunberg

[zsunberg]

Yep, this is what I had in mind! except there should also be a convert(::Type{<:RLBase.AbstractEnv}, env::CommonRLInterface.CommonEnv)

[findmyway]

I'll clean up APIs in RLBase a little and then work on this issue together with JuliaReinforcementLearning/CommonRLInterface.jl#18 (comment) in the next week.

[findmyway]

Supported in RLBase directly. JuliaReinforcementLearning/ReinforcementLearningBase.jl-Archive#58