search

sentenai / reinforce

Reinforcement learning in haskell
https://sentenai.github.io/reinforce/
BSD 3-Clause "New" or "Revised" License
44 stars 17 forks source link

Clean up and formalize State- and Action-Space typeclasses #3

Open stites opened 7 years ago

stites commented 7 years ago

Currently, there is only a half-baked state space in a poorly-named module. Action spaces are presumed only to be bounded enums (ie: discrete spaces, but we should also account for Box and continuous). This should be moved and functions should be added to so that a user can make state- and action- based informational queries.

stites commented 7 years ago

Hopefully, this abstraction comes out of writing more agents.