ast_toolbox.algos.mctsrs module¶
-
class
ast_toolbox.algos.mctsrs.
MCTSRS
(seed=0, rsg_length=1, **kwargs)[source]¶ Bases:
ast_toolbox.algos.mcts.MCTS
Monte Carlo Tress Search (MCTS) with double progressive widening (DPW) [1] using the random seeds as its action space.
Parameters: - seed (int, optional) – The seed used to generate the initial random seed generator.
- rsg_length (int, optional) – The length of the state of the random seed generator. Set it to higher values for extreme large problems.
References
[1] Lee, Ritchie, et al. “Adaptive stress testing of airborne collision avoidance systems.” 2015 IEEE/AIAA 34th Digital Avionics Systems Conference (DASC). IEEE, 2015.