Open rlipkis opened 3 years ago
You're absolutely correct. This has been an extension to the GrayBox
interface I've been planning on for a while. I'll take a look at your approach and let you know if that's the generic design that fits within this package. Nevertheless, we'll converge to allow some explicit state in this framework.
Glad to see you're using this package, and I remember you from CS238 👋
I recently pushed changes based on your fork to include explicit GrayBox.state
information (instead of the sim.hash).
Hi! I've been using your package, and I've run into an issue with the DRL solvers.
The function
get_action
passes the state into the neural networkpolicy.μ
, but this state is computed inconvert_s
to be the hash of theASTState
. My impression is that a hash value is not really a meaningful input to a NN, and it seems like it would invalidate much of the learning, effectively reducing the DRL algorithms to a random search.If the
GrayBox
interface is extended to allow aVector{Float64}
state to be specified and stored in theASTState
at each update, this can be extracted inconvert_s
and passed into the NN. I've made those changes in my local copy to get things working, but perhaps there's a solution that's more in line with your vision for the package, in terms of genericity, etc. If you'd like, I can submit a pull request.