mpcrl.core.exploration.NoExploration

class mpcrl.core.exploration.NoExploration

Bases: ExplorationStrategy

Strategy where no exploration is allowed at any time or, in other words, the policy is always deterministic (only based on the current state, and not perturbed).

Notes

This is a special kind of ExplorationStrategy, the only one without any hook and mode.

Methods

can_explore()	Computes whether, according to the exploration strategy, the agent should explore or not now, at the current instant.
perturbation(*args, **kwargs)	Returns a random perturbation.
reset([_])	Resets the exploration status, in case it is non-deterministic.
step(*_, **__)	Does nothing, since no exploration is allowed.

Attributes

hook	Returns None, since no exploration is allowed.
mode	Returns None, since no exploration is allowed.

can_explore()

Computes whether, according to the exploration strategy, the agent should explore or not now, at the current instant.

Returns:

bool

True if the agent should explore according to this strategy; otherwise, False.

Return type:

bool

property hook: None

Returns None, since no exploration is allowed.

property mode: None

Returns None, since no exploration is allowed.

perturbation(*args, **kwargs)

Returns a random perturbation.

Return type:

ndarray[tuple[Any, ...], dtype[floating]]

reset(_=None)

Resets the exploration status, in case it is non-deterministic.

Return type:

None

step(*_, **__)

Does nothing, since no exploration is allowed.

Return type:

None