sp
/
tempest
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
3500 Commits
2 Branches
0 Tags
187 MiB
Tree: 29f0f66689
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '29f0f66689'
${ noResults }
Commit Graph

39 Commits (29f0f66689c6fd5fccf4dadd3ddeb6a9d3168967)

Author SHA1 Message Date
dehnert 29f0f66689 reworked getUniqueRewardModel a little
9 years ago
sjunges 548ba8bbeb somehow managed my way through the policy guessing, several minor extensions to solvers
9 years ago
sjunges 31228486d3 towards merging, including a extension on the pstateeliminator, come back after generalizing the lra eliminator
9 years ago
TimQu da0dafe5be ModelInstantiator!!!!11
9 years ago
TimQu 8297c51d73 Fixed a bug that was not yet fixed for some reason...
9 years ago
TimQu 1225b056f2 a little refactoring
10 years ago
TimQu 8ab7cae974 early termination
10 years ago
TimQu 91fb664910 Refactored a little and implemented functions for prophesy
10 years ago
TimQu f3f3a31e1e Optimization for policy recycling
10 years ago
TimQu 9c645ba24b Work on policy recycling
10 years ago
TimQu dae0faa2a0 refactored the quick implementation of the recent bugfix
10 years ago
TimQu 87c8241ec7 policies for games
10 years ago
TimQu bf450688b4 The variable pool of carl needs to be cleared after executing a test.
10 years ago
TimQu 0863d0e51a don't store ALL the occurring policies...
10 years ago
TimQu ca917a651c MinMaxLinearEqSolvers can now use some initial policy as a first guess.
10 years ago
TimQu e80a1081bb First steps to identify the parameters for which the optimal policy always choses the same boundary
10 years ago
TimQu 6ddddd8cfa Implemented policy extraction for value iteration
10 years ago
TimQu 1860502a3a Deterministic states with only constant outgoing transitions are now eliminated
10 years ago
TimQu 77c2f397a9 fix for approximation model, additional test for mdps, minor changes
10 years ago
TimQu c53b79b9b7 approximation model, again
10 years ago
TimQu 67ff27954e refactored approximation model (almost done)
10 years ago
TimQu 77e086f446 small fix regarding the return type of computeValue
10 years ago
TimQu f72c30cdff First version of approximation model (with mdp intead of s2pg)
10 years ago
TimQu 78bd4a041a Added Mdp class, sampling might work already (untested)
10 years ago
TimQu 70dd76c08b Splitted region modelchecker in abstract class and dtmc class (to easily add an mdp class soon)
10 years ago
TimQu 0043d3ebf5 changed template argument, used unordered_map
10 years ago
TimQu 5b1494b9a9 Made use of this new cool rewardModel thing
10 years ago
TimQu d377e6b289 Minor improvements everywhere. Also implemented some tests
10 years ago
TimQu c4444567e7 further optimization on approximation model initialization. Also better code structure of preprocessing steps
10 years ago
TimQu af505c7e89 Faster and more structured initialization of approx and sampling model
10 years ago
TimQu d57551c1ec Fix for solver
10 years ago
TimQu 37a7b392f6 First version of approximation for rewards
10 years ago
TimQu d0f7e5f6da First steps towards working with rewards
10 years ago
TimQu efadc84593 Beautified the Code, removed unused stuff, minor improvements
10 years ago
TimQu 28326b14e4 more efficient instantiation of matrices.
10 years ago