sampleExperience: Sample state transitions from an environment function

Description Usage Arguments Value See Also Examples

View source: R/sampleExperience.R

Description

Function generates sample experience in the form of state transition tuples.

Usage

1
2
3
sampleExperience(N, env, states, actions, actionSelection = "random",
  control = list(alpha = 0.1, gamma = 0.1, epsilon = 0.1),
  model = NULL, ...)

Arguments

N

Number of samples.

env

An environment function.

states

A character vector defining the enviroment states.

actions

A character vector defining the available actions.

actionSelection

(optional) Defines the action selection mode of the reinforcement learning agent. Default: random.

control

(optional) Control parameters defining the behavior of the agent. Default: alpha = 0.1; gamma = 0.1; epsilon = 0.1.

model

(optional) Existing model of class rl. Default: NULL.

...

Additional parameters passed to function.

Value

An dataframe containing the experienced state transition tuples s,a,r,s_new. The individual columns are as follows:

State

The current state.

Action

The selected action for the current state.

Reward

The reward in the current state.

NextState

The next state.

See Also

ReinforcementLearning

gridworldEnvironment

Examples

1
2
3
4
5
6
7
8
9
# Define environment
env <- gridworldEnvironment

# Define states and actions
states <- c("s1", "s2", "s3", "s4")
actions <- c("up", "down", "left", "right")

# Sample 1000 training examples
data <- sampleExperience(N = 1000, env = env, states = states, actions = actions)

ReinforcementLearning documentation built on March 26, 2020, 7:38 p.m.