EconBase
← All papers

A Relation Analysis of Markov Decision Process Frameworks

Tien Mai, Patrick Jaillet

arXiv 18 Aug 2020 · Mathematics — Optimization · 2 citations (OpenAlex)

arXiv:2008.07820 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We study the relation between different Markov Decision Process (MDP) frameworks in the machine learning and econometrics literatures, including the standard MDP, the entropy and general regularized MDP, and stochastic MDP, where the latter is based on the assumption that the reward function is stochastic and follows a given distribution. We show that the entropy-regularized MDP is equivalent to a stochastic MDP model, and is strictly subsumed by the general regularized MDP. Moreover, we propose a distributional stochastic MDP framework by assuming that the distribution of the reward function is ambiguous. We further show that the distributional stochastic MDP is equivalent to the regularized MDP, in the sense that they always yield the same optimal policies. We also provide a connection between stochastic/regularized MDP and constrained MDP. Our work gives a unified view on several important MDP frameworks, which would lead new ways to interpret the (entropy/general) regularized MDP frameworks through the lens of stochastic rewards and vice-versa. Given the recent popularity of regularized MDP in (deep) reinforcement learning, our work brings new understandings of how such algorithmic schemes work and suggest ideas to develop new ones.

Citation extraction

32
references
71
in-text mentions
32
distinct cited
0
self-citations
7,273
main-text words

appendix boundary found by appendix_command · 50% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Brian D Ziebart, J Andrew Bagnell, and Anind K Dey (2010) Modeling interaction via the principle of maximum causal entropy1.00074100%
2Rust John (1988) Maximum likelihood estimation of discrete control processes1.00063100%
3Matthieu Geist, Bruno Scherrer, and Olivier Pietquin (2019) A theory of regularized markov decision processes0.9285380%
4John Rust (1987) Optimal replacement of gmc bus engines: An empirical model of harold zurcher0.9285380%
5Karthik Natarajan, Miao Song, and Chung-Piaw Teo (2009) Persistency model and its applications in choice modeling0.87452100%
6Abbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa, Remi Munos… (1806) Maximum a posteriori policy optimisation0.84333100%
7Tuomas Haarnoja, Haoran Tang, Pieter Abbeel, and Sergey Levine (2017) Reinforcement learning with deep energy-based policies0.7373367%
8Abbas Abdolmaleki, Jost Tobias Springenberg, Jonas Degrave, Steven B… (1812) Relative entropy regularized policy iteration0.64422100%
9Eitan Altman (1999) Constrained Markov decision processes, volume 70.64422100%
10Mohammad Gheshlaghi Azar, Vicenc Gómez, and Hilbert J Kappen (2012) Dynamic policy programming0.64422100%

Showing the top 10 of 32 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Constrained Recursive Logit for Route Choice Analysis0.64422