Struct MultiAgentEnvLoop 

pub struct MultiAgentEnvLoop<BT: Backend, RLC: RLComponentsTypes> { /* private fields */ }

Available on crate feature rl only.

An asynchronous runner for multiple agent/environement interfaces.

Implementations

impl<BT: Backend, RLC: RLComponentsTypes> MultiAgentEnvLoop<BT, RLC>

pub fn new( num_envs: usize, env_init: RLC::EnvInit, agent: AsyncPolicy<RLC::Backend, RLC::Policy>, eval: bool, deterministic: bool, device: &Device<BT>, ) -> Self

Create a new asynchronous runner for multiple agent/environement interfaces.

Trait Implementations

impl<BT, RLC> AgentEnvLoop<BT, RLC> for MultiAgentEnvLoop<BT, RLC>

where BT: Backend, RLC: RLComponentsTypes,

fn run_steps( &mut self, num_steps: usize, processor: &mut RLEventProcessorType<RLC>, interrupter: &Interrupter, progress: &mut Progress, ) -> Vec<TimeStep<BT, <RLC as RLComponentsTypes>::State, <RLC as RLComponentsTypes>::Action, <RLC as RLComponentsTypes>::ActionContext>>

Run a certain number of timesteps.

fn update_policy(&mut self, update: RLC::PolicyState)

Update the runner’s agent.

fn run_episodes( &mut self, num_episodes: usize, processor: &mut RLEventProcessorType<RLC>, interrupter: &Interrupter, _progress: &mut Progress, ) -> Vec<Trajectory<BT, <RLC as RLComponentsTypes>::State, <RLC as RLComponentsTypes>::Action, <RLC as RLComponentsTypes>::ActionContext>>

Run a certain number of episodes.

fn policy(&self) -> RLC::PolicyState

Get the state of the runner’s agent.