[−][src]Struct connect6::policy::AlphaZero
Implementation of policy AlphaZero
based on combined MCTS with non-linear value approximator.
AlphaZero
policy is implemented based on Mastering the game of Go with deep neural networks and tree search
and Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm.
Examples
let param = HyperParameter::light_weight(); let mut policy = AlphaZero::with_param(Box::new(RandomEvaluator {}), param); let result = Agent::new(&mut policy).play(); assert!(result.is_ok());
Methods
impl AlphaZero
[src]
pub fn new(evaluator: Box<dyn Evaluator + Send>) -> AlphaZero
[src]
Construct a new AlphaZero
policy with given evalueator
pub fn with_param(
evaluator: Box<dyn Evaluator + Send>,
param: HyperParameter
) -> AlphaZero
[src]
evaluator: Box<dyn Evaluator + Send>,
param: HyperParameter
) -> AlphaZero
Construct a AlphaZero
with given hyperparam
Trait Implementations
Auto Trait Implementations
Blanket Implementations
impl<T> From for T
[src]
impl<T, U> Into for T where
U: From<T>,
[src]
U: From<T>,
impl<T, U> TryFrom for T where
T: From<U>,
[src]
T: From<U>,
type Error = !
🔬 This is a nightly-only experimental API. (
try_from
)The type returned in the event of a conversion error.
fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>
[src]
impl<T> Borrow for T where
T: ?Sized,
[src]
T: ?Sized,
impl<T> BorrowMut for T where
T: ?Sized,
[src]
T: ?Sized,
fn borrow_mut(&mut self) -> &mut T
[src]
impl<T, U> TryInto for T where
U: TryFrom<T>,
[src]
U: TryFrom<T>,
type Error = <U as TryFrom<T>>::Error
🔬 This is a nightly-only experimental API. (
try_from
)The type returned in the event of a conversion error.
fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>
[src]
impl<T> Any for T where
T: 'static + ?Sized,
[src]
T: 'static + ?Sized,