[−][src]Trait rsrl_domains::Domain
An interface for constructing reinforcement learning problem domains.
Associated Types
type StateSpace: Space
State space representation type class.
type ActionSpace: Space
Action space representation type class.
Required methods
fn state_space(&self) -> Self::StateSpace
Returns an instance of the state space type class.
fn action_space(&self) -> Self::ActionSpace
Returns an instance of the action space type class.
fn emit(&self) -> Observation<State<Self>>
Emit an observation of the current state of the environment.
fn step(&mut self, a: &Action<Self>) -> (Observation<State<Self>>, Reward)
Transition the environment forward a single step given an action, a
.
Provided methods
fn transition(
&mut self,
a: Action<Self>
) -> Transition<State<Self>, Action<Self>>
&mut self,
a: Action<Self>
) -> Transition<State<Self>, Action<Self>>
fn rollout<F>(
self,
pi: F,
step_limit: Option<usize>
) -> Trajectory<State<Self>, Action<Self>> where
F: FnMut(&State<Self>) -> Action<Self>,
Self: Sized,
self,
pi: F,
step_limit: Option<usize>
) -> Trajectory<State<Self>, Action<Self>> where
F: FnMut(&State<Self>) -> Action<Self>,
Self: Sized,