Move TRPO/PPO to new package: PolicyOptimization.jl

sisl / POMDPStressTesting.jl

Adaptive stress testing of black-box systems within POMDPs.jl

Other

13 stars 5 forks source link

Move TRPO/PPO to new package: PolicyOptimization.jl #1

Open mossr opened 4 years ago

mossr commented 4 years ago

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 commented 4 years ago

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

mossr commented 4 years ago

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

MaximeBouton commented 4 years ago

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