LIRRA  1.0.0
Loading...
Searching...
No Matches
rl_stl.evaluation.patrol.ExpertProposer Class Reference

Public Member Functions

 __init__ (self, RecedingProblem problem, ISTLSettings settings=ISTLSettings(time_limit=2.0), float|np.ndarray noise=0.0, int seed=0)
 
np.ndarray __call__ (self, ProposalContext ctx)
 

Public Attributes

 problem
 
 settings
 
 noise
 
 rng
 
 last
 

Detailed Description

Solves the synthesis problem itself (rooted at the measured state): an ideal policy.

Used to generate behaviour-cloning data and as an upper bound on what a learned proposer
can achieve. ``noise`` (scalar or per input) adds Gaussian noise to its output, clipped to
the input box (imperfect-learner stand-in).

Constructor & Destructor Documentation

◆ __init__()

rl_stl.evaluation.patrol.ExpertProposer.__init__ (   self,
RecedingProblem  problem,
ISTLSettings   settings = ISTLSettings(time_limit=2.0),
float | np.ndarray   noise = 0.0,
int   seed = 0 
)

Member Function Documentation

◆ __call__()

np.ndarray rl_stl.evaluation.patrol.ExpertProposer.__call__ (   self,
ProposalContext  ctx 
)

Member Data Documentation

◆ last

rl_stl.evaluation.patrol.ExpertProposer.last

◆ noise

rl_stl.evaluation.patrol.ExpertProposer.noise

◆ problem

rl_stl.evaluation.patrol.ExpertProposer.problem

◆ rng

rl_stl.evaluation.patrol.ExpertProposer.rng

◆ settings

rl_stl.evaluation.patrol.ExpertProposer.settings

The documentation for this class was generated from the following file: