Summary of Learning General Parameterized Policies For Infinite Horizon Average Reward Constrained Mdps Via Primal-dual Policy Gradient Algorithm, by Qinbo Bai et al.
Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
by Qinbo Bai, Washim Uddin Mondal, Vaneet Aggarwal
First submitted to arxiv on: 3 Feb 2024
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 This paper delves into the realm of infinite horizon average reward Constrained Markov Decision Processes (CMDPs), a previously unexplored area. The authors propose a primal dual-based policy gradient algorithm that balances constraints while ensuring low regret towards achieving an optimal policy. Notably, this algorithm achieves objective regret and constraint violation bounds of ({T}^{4/5}). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary CMDPs are a type of Markov Decision Process where the goal is to find the best policy for maximizing the average reward over an infinite horizon. This paper looks at how to analyze the regret and constraint violation in CMDPs with general policies. The authors propose an algorithm that balances the constraints while trying to achieve an optimal policy. |
