sritchie / scala-rl

Functional Reinforcement Learning in Scala.
https://www.scalarl.com
Apache License 2.0
26 stars 5 forks source link

Chapter 3 + Gridworld #7

Closed sritchie closed 5 years ago

sritchie commented 5 years ago

This PR gets a gridworld going. This SHOULD, I expect, force policies to have to know about states and values, not just values.

That'll force a decision on how to write an Equiv instance on states, and how to generate identifiers for states.