Struct border::env::py_gym_env::base::PyGymEnv

pub struct PyGymEnv<O, A, OF, AF> where
    O: Obs,
    A: Act,
    OF: PyGymEnvObsFilter<O>,
    AF: PyGymEnvActFilter<A>,  { /* fields omitted */ }

Represents an environment in OpenAI gym. The code is adapted from tch-rs RL example.

Implementations

impl<O, A, OF, AF> PyGymEnv<O, A, OF, AF> where
    O: Obs,
    A: Act,
    OF: PyGymEnvObsFilter<O>,
    AF: PyGymEnvActFilter<A>, 

pub fn new(
    name: &str,
    obs_filter: OF,
    act_filter: AF,
    atari_wrapper: Option<AtariWrapper>
) -> PyResult<Self>

Constructs an environment.

name is the name of the environment, which is implemented in OpenAI gym.

pub fn set_render(&mut self, render: bool)

Set rendering mode.

If true, it renders the state at every step.

pub fn max_steps(self, v: Option<usize>) -> Self

Set the maximum number of steps in the environment.

pub fn set_wait_in_render(&mut self, d: Duration)

Set time for sleep in rendering.

pub fn get_num_actions_atari(&self) -> i64

Get the number of available actions of atari environments

Trait Implementations

impl<O: Debug, A: Debug, OF: Debug, AF: Debug> Debug for PyGymEnv<O, A, OF, AF> where
    O: Obs,
    A: Act,
    OF: PyGymEnvObsFilter<O>,
    AF: PyGymEnvActFilter<A>, 

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<O, A, OF, AF> Env for PyGymEnv<O, A, OF, AF> where
    O: Obs,
    A: Act + Debug,
    OF: PyGymEnvObsFilter<O>,
    AF: PyGymEnvActFilter<A>, 

fn reset(&mut self, is_done: Option<&Vec<i8>>) -> Result<O, Box<dyn Error>>

Resets the environment, the obs/act filters and returns the observation tensor.

In this environment, the length of is_done is assumed to be 1.

TODO: defines appropriate error for the method and returns it.

fn step(&mut self, a: &A) -> (Step<Self>, Record)

Runs a step of the environment’s dynamics.

It returns Step and Record objects. The Record is composed of Records constructed in PyGymEnvObsFilter and PyGymEnvActFilter.

type Obs = O

Observation of the environment.

type Act = A

Action of the environment.

type Info = PyGymInfo

Information in the self::Step object.