env_monitor_start: Start monitoring.

In gym: Provides Access to the OpenAI Gym API

Description

Start monitoring.

Usage

env_monitor_start(x, instance_id, directory, force = FALSE, resume = FALSE)

Arguments

x	An instance of class "GymClient"; this object has "remote_base" as an attribute.
instance_id	A short identifier (such as "3c657dbc") for the environment instance.
directory	The directory to write the training data to. Defaults to FALSE.
force	Clear out existing training data from this directory (by deleting every file prefixed with "openaigym"). Defaults to NULL.
resume	Retain the training data already in this directory, which will be merged with our new data. Defaults to FALSE.

Value

NULL.

Examples

## Not run: 
remote_base <- "http://127.0.0.1:5000"
client <- create_GymClient(remote_base)
env_id <- "CartPole-v0"
instance_id <- env_create(client, env_id)
outdir <- "/tmp/random-agent-results"
env_monitor_start(client, instance_id, outdir, force = TRUE, resume = FALSE)

## End(Not run)

gym documentation built on May 1, 2019, 9:26 p.m.