Strategy Representation by Decision Trees with Linear Classifiers

06/19/2019
by   Pranav Ashok, et al.
0

Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of ω-regular winning conditions; e.g., safety, reachability, liveness, parity conditions; provides a robust and expressive specification formalism for properties that arise in analysis of reactive systems. The resolutions of nondeterminism in games and MDPs are represented as strategies, and we consider succinct representation of such strategies. The decision-tree data structure from machine learning retains the flavor of decisions of strategies and allows entropy-based minimization to obtain succinct trees. However, in contrast to traditional machine-learning problems where small errors are allowed, for winning strategies in graph games and MDPs no error is allowed, and the decision tree must represent the entire strategy. In this work we propose decision trees with linear classifiers for representation of strategies in graph games and MDPs. We have implemented strategy representation using this data structure and we present experimental results for problems on graph games and MDPs, which show that this new data structure presents a much more efficient strategy representation as compared to standard decision trees.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/02/2018

Strategy Representation by Decision Trees in Reactive Synthesis

Graph games played by two players over finite-state graphs are central i...
research
06/25/2019

SOS: Safe, Optimal and Small Strategies for Hybrid Markov Decision Processes

For hybrid Markov decision processes, UPPAAL Stratego can compute strate...
research
01/30/2023

Optimal Decision Tree Policies for Markov Decision Processes

Interpretability of reinforcement learning policies is essential for man...
research
07/06/2017

Efficient Strategy Iteration for Mean Payoff in Markov Decision Processes

Markov decision processes (MDPs) are standard models for probabilistic s...
research
04/10/2018

Combinations of Qualitative Winning for Stochastic Parity Games

We study Markov decision processes and turn-based stochastic games with ...
research
04/25/2018

Distribution-based objectives for Markov Decision Processes

We consider distribution-based objectives for Markov Decision Processes ...
research
01/15/2021

dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts

Recent advances have shown how decision trees are apt data structures fo...

Please sign up or login with your details

Forgot password? Click here to reset