Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning

Pranav Khanna; Guy Tennenholtz; Nadav Merlis; Shie Mannor; Chen Tessler

Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning

Pranav Khanna, Guy Tennenholtz, Nadav Merlis, Shie Mannor, Chen Tessler

Technion - Israel Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

Original language	English
Pages (from-to)	2430-2432
Number of pages	3
Journal	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume	2023-May
State	Published - 2023
Event	22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023 - London, United Kingdom Duration: 29 May 2023 → 2 Jun 2023

Keywords

Deep Learning
Reinforcement Learning
Stability

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence
Control and Systems Engineering

Access to Document

https://dl.acm.org/doi/pdf/10.5555/3545946.3598957

Cite this

@article{4dbac00ddd0944ea99fcc144f62c2163,

title = "Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning",

keywords = "Deep Learning, Reinforcement Learning, Stability",

author = "Pranav Khanna and Guy Tennenholtz and Nadav Merlis and Shie Mannor and Chen Tessler",

year = "2023",

language = "الإنجليزيّة",

volume = "2023-May",

pages = "2430--2432",

journal = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",

issn = "1548-8403",

publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

note = "22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023 ; Conference date: 29-05-2023 Through 02-06-2023",

}

TY - JOUR

T1 - Never Worse, Mostly Better

T2 - 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023

AU - Khanna, Pranav

AU - Tennenholtz, Guy

AU - Merlis, Nadav

AU - Mannor, Shie

AU - Tessler, Chen

PY - 2023

Y1 - 2023

KW - Deep Learning

KW - Reinforcement Learning

KW - Stability

UR - http://www.scopus.com/inward/record.url?scp=85171281638&partnerID=8YFLogxK

M3 - مقالة من مؤنمر

SN - 1548-8403

VL - 2023-May

SP - 2430

EP - 2432

JO - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

JF - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

Y2 - 29 May 2023 through 2 June 2023

ER -

Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this