sampleExperience: Sample state transitions from an environment function
In nproellochs/ReinforcementLearning: Model-Free Reinforcement Learning

Description Usage Arguments Value See Also Examples

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

1
2
3

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

`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.

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.

ReinforcementLearning

gridworldEnvironment

# 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)