Move TRPO/PPO to new package: PolicyOptimization.jl

[mossr]

The TRPO and PPO implementations are general enough to be in their own solver package in the POMDPs.jl ecosystem. I've already encapsulated these solvers into the DeepRL module.

Some TODOs:

• Extract AST specific code and generalize TRPO and PPO solvers
• Test on different POMDPs.jl example

Among other things to be appended to this list.

[MaximeBouton]

Maybe they could be a TRPO.jl and PPO.jl ? or PolicyOptimization.jl with both?

[mossr]

Agreed. They share a lot of base code, so I like PolicyOptimization.jl over DeepRL.jl.

[MaximeBouton]

cool, then that is kind of consistent with DeepQLearning.jl
RLInterface will need to be registered to general before you register PolicyOptimization.jl btw