The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

gym

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)

# Create environment
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

• The original author of gym is Paul Hendricks.

• The lead maintainer of gym is Paul Hendricks.

License

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.