Summary of Intervention Efficient Algorithm For Two-stage Causal Mdps, by Rahul Madhavan et al.
Intervention Efficient Algorithm for Two-Stage Causal MDPs
by Rahul Madhavan, Aurghya Maiti, Gaurav Sinha, Siddharth Barman
First submitted to arxiv on: 1 Nov 2021
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper develops a new framework for Markov Decision Processes (MDPs) where states are causal graphs that stochastically generate rewards. The goal is to identify atomic interventions that lead to high rewards by intervening on variables at each state. Building upon the causal-bandit framework, the work provides regret minimization guarantees for two-stage causal MDPs with parallel causal graphs at each state. An algorithm is proposed that achieves an instance-dependent regret bound using convex optimization to address the exploration problem. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better understand how to make good decisions in situations where we don’t know all the rules. Imagine you’re trying to find the best way to get a reward, but you can’t see what’s happening because there are lots of unknown variables. The researchers created a new way to solve this problem using something called Markov Decision Processes (MDPs). They also developed an algorithm that helps us make good choices by finding the right times and places to intervene in the process. |
Keywords
* Artificial intelligence * Optimization
