Provides Access to the OpenAI Gym API

OpenAI Gym is a open-source Python toolkit for developing and comparing reinforcement learning algorithms. This is a wrapper for the OpenAI Gym API, and enables access to an ever-growing variety of environments. For more details on OpenAI Gym, please see here: < https://github.com/openai/gym>. For more details on the OpenAI Gym API specification, please see here: < https://github.com/openai/gym-http-api>.


Project Status: Active - The project has reached a stable, usable state and is being actively developed.

OpenAI Gym is a open-source Python toolkit for developing and comparing reinforcement learning algorithms. This R package is a wrapper for the OpenAI Gym API, and enables access to an ever-growing variety of environments.

Installation

You can install:

  • the latest released version from CRAN:

    install.packages("gym")
  • the latest development version from Github:

    if (packageVersion("devtools") < 1.6) {
      install.packages("devtools")
    }
    devtools::install_github("paulhendricks/gym-R", subdir = "gym")

If you encounter a clear bug, please file a minimal reproducible example on github.

API

library(gym)
 
remote_base <- "http://127.0.0.1:5000"
client <- create_GymClient(remote_base)
print(client)
env_id <- "CartPole-v0"
instance_id <- env_create(client, env_id)
print(instance_id)
 
# List all environments
all_envs <- env_list_all(client)
print(all_envs)
 
# Set up agent
action_space_info <- env_action_space_info(client, instance_id)
print(action_space_info)
agent <- random_discrete_agent(action_space_info[["n"]])
 
# Run experiment, with monitor
outdir <- "/tmp/random-agent-results"
env_monitor_start(client, instance_id, outdir, force = TRUE, resume = FALSE)
 
episode_count <- 100
max_steps <- 200
reward <- 0
done <- FALSE
 
for (i in 1:episode_count) {
  ob <- env_reset(client, instance_id)
  for (i in 1:max_steps) {
    action <- env_action_space_sample(client, instance_id)
    results <- env_step(client, instance_id, action, render = TRUE)
    if (results[["done"]]) break
  }
}
 
# Dump result info to disk
env_monitor_close(client, instance_id)

People

License

License

News

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("gym")

0.1.0 by Paul Hendricks, 2 years ago


https://github.com/paulhendricks/gym-R


Report a bug at https://github.com/paulhendricks/gym-R/issues


Browse source code at https://github.com/cran/gym


Authors: Paul Hendricks [aut, cre]


Documentation:   PDF Manual  


MIT + file LICENSE license


Imports httr, jsonlite

Suggests testthat


See at CRAN