reinforcelearn
reinforcelearn copied to clipboard
markusdumke
R Package for Reinforcement Learning
Hi, I've been playing with this library, but have some trouble setting up a toy example. I want to learn an agent to eat a cake. The reward is the...
I have been working through the Agents vignette (https://cran.rstudio.com/web/packages/reinforcelearn/vignettes/agents.html) and I found a few errors. 1. In the "Value Functions" section, half way down, there is sample code following "For...
library(reinforcelearn) library(keras) library(tidyverse) model = keras_model_sequential() model %>% layer_dense(20, input_shape = 10, activation = "relu") model %>% layer_dense(4, activation = "softmax") keras::compile(model, loss = "mae", optimizer = keras::optimizer_sgd(lr = 0.4))...
Hi @markusdumke I am trying to let an agent interact with the OpenAI MountainCar gym as seen here: ``` library(reinforcelearn) # create gym env env = makeEnvironment("gym", gym.name = "MountainCar-v0")...
consider this: ``` set.seed(123) library(keras) load_all() env = mountainCar() preprocessState = function(state) { state[1, , drop = FALSE] } m = keras_model_sequential() m %>% layer_dense(input_shape = 2, activation = "relu",...
it MUST be precisely documented what data type the function shall return. a feature vector? a matrix? depends on the model? if multiple things are possible, please say so and...