markusdumke/reinforcelearn

can we visualize policy steps and what happens during learning?

berndbischl opened this issue · 1 comments

berndbischl commented

it would be nice if i can see what happens

markusdumke commented 
library(reinforcelearn)
env = makeEnvironment("gridworld", shape = c(3, 3), goal.states = 1)
agent = makeAgent(policy = "random")
interact(env, agent, n.steps = 2, visualize = TRUE)