# On the impact of MDP design for Reinforcement Learning agents in Resource Management

arXiv: https://arxiv.org/abs/2109.03202 · HTML: https://mlsanity.com/paper/2109.03202/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 7 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [State of the Art Control of Atari Games Using Shallow Reinforcement Learning](https://mlsanity.com/paper/1512.01563/) (2015)
- [Deep Reinforcement Agent for Scheduling in HPC](https://mlsanity.com/paper/2102.06243/) (2021)
- [Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data](https://mlsanity.com/paper/2003.14229/) (2020)
- [Job Placement Advisor Based on Turnaround Predictions for HPC Hybrid Clouds](https://mlsanity.com/paper/1608.06310/) (2016)

## Built on by (most cited first, 1 of 1)

- [Reinforcement Learning for Location-Aware Scheduling](https://mlsanity.com/paper/2203.03480/) (2022)

## Abstract (arXiv)

The recent progress in Reinforcement Learning applications to Resource Management presents MDPs without a deeper analysis of the impacts of design decisions on agent performance. In this paper, we compare and contrast four different MDP variations, discussing their computational requirements and impacts on agent performance by means of an empirical analysis. We conclude by showing that, in our experiments, when using Multi-Layer Perceptrons as approximation function, a compact state representation allows transfer of agents between environments, and that transferred agents have good performance and outperform specialized agents in 80% of the tested scenarios, even without retraining.