Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2211.00241
Cited By
v1
v2
v3
v4 (latest)
Adversarial Policies Beat Superhuman Go AIs
International Conference on Machine Learning (ICML), 2022
1 November 2022
T. T. Wang
Adam Gleave
Tom Tseng
Kellin Pelrine
Nora Belrose
Joseph Miller
Michael Dennis
Yawen Duan
V. Pogrebniak
Sergey Levine
Stuart Russell
AAML
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"Adversarial Policies Beat Superhuman Go AIs"
21 / 21 papers shown
Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning
Richard Dewey
Janos Botyanszki
C. Moallemi
Andrew Zheng
163
0
0
05 Nov 2025
Look-ahead Reasoning with a Learned Model in Imperfect Information Games
Ondřej Kubíček
Viliam Lisý
LRM
104
0
0
06 Oct 2025
Relevance-Zone Reduction in Game Solving
Chi-Huang Lin
Ting Han Wei
Chun-Jui Wang
Hung Guei
Chung-Chin Shih
Yun-Jui Tsai
I-Chen Wu
Ti-Rong Wu
97
0
0
01 Oct 2025
Virtual Agent Economies
Nenad Tomašev
Matija Franklin
Joel Z. Leibo
Julian Jacobs
William A. Cunningham
Iason Gabriel
Simon Osindero
180
6
0
12 Sep 2025
LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning
Cole Robertson
Philip Wolff
61
0
0
21 Jul 2025
TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models
Yang Dai
Oubo Ma
Longfei Zhang
Xingxing Liang
Xiaochun Cao
Shouling Ji
J. Zhang
Jincai Huang
Li Shen
234
0
0
15 Jun 2025
The Structural Safety Generalization Problem
Annual Meeting of the Association for Computational Linguistics (ACL), 2025
Julius Broomfield
Tom Gibbs
Ethan Kosak-Hine
George Ingebretsen
Tia Nasir
Jason Zhang
Reihaneh Iranmanesh
Sara Pieri
Reihaneh Rabbany
Kellin Pelrine
AAML
396
1
0
13 Apr 2025
UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
Oubo Ma
L. Du
Yang Dai
Chunyi Zhou
Qingming Li
Yuwen Pu
R. Beyah
339
3
0
28 Jan 2025
Demystifying MuZero Planning: Interpreting the Learned Model
IEEE Transactions on Artificial Intelligence (IEEE TAI), 2024
Hung Guei
Yan-Ru Ju
Wei-Yu Chen
Tai-Lin Wu
283
2
0
07 Nov 2024
Bridging Local and Global Knowledge via Transformer in Board Games
International Joint Conference on Artificial Intelligence (IJCAI), 2024
Tai-Lin Wu
Tai-Lin Wu
Chung-Chin Shih
Yan-Ru Ju
AAML
250
0
0
07 Oct 2024
Scaling Trends in Language Model Robustness
Nikolhaus Howe
Michal Zajac
I. R. McKenzie
Oskar Hollinsworth
Tom Tseng
Aaron David Tucker
Pierre-Luc Bacon
Adam Gleave
647
1
0
25 Jul 2024
Games of Knightian Uncertainty as AGI testbeds
Spyridon Samothrakis
Dennis J. N. J. Soemers
Damian Machlanski
284
1
0
26 Jun 2024
Open-Endedness is Essential for Artificial Superhuman Intelligence
International Conference on Machine Learning (ICML), 2024
Edward Hughes
Michael Dennis
Jack Parker-Holder
Feryal M. P. Behbahani
Aditi Mavalankar
Yuge Shi
Tom Schaul
Tim Rocktaschel
LRM
338
56
0
06 Jun 2024
SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
Conference on Computer and Communications Security (CCS), 2024
Oubo Ma
Yuwen Pu
L. Du
Yang Dai
Ruo Wang
Xiaolei Liu
Yingcai Wu
Shouling Ji
AAML
281
13
0
06 Feb 2024
Black-Box Access is Insufficient for Rigorous AI Audits
Conference on Fairness, Accountability and Transparency (FAccT), 2024
Stephen Casper
Carson Ezell
Charlotte Siegmann
Noam Kolt
Taylor Lynn Curtis
...
Michael Gerovitch
David Bau
Max Tegmark
David M. Krueger
Dylan Hadfield-Menell
AAML
560
133
0
25 Jan 2024
Multi-Agent Diagnostics for Robustness via Illuminated Diversity
Adaptive Agents and Multi-Agent Systems (AAMAS), 2024
Mikayel Samvelyan
Davide Paglieri
Minqi Jiang
Jack Parker-Holder
Tim Rocktaschel
AAML
330
5
0
24 Jan 2024
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
Adaptive Agents and Multi-Agent Systems (AAMAS), 2023
Daniel Bairamian
Philippe Marcotte
Joshua Romoff
Gabriel Robert
Derek Nowrouzezahrai
202
1
0
28 Nov 2023
Managing extreme AI risks amid rapid progress
Yoshua Bengio
Geoffrey Hinton
Andrew Yao
Dawn Song
Pieter Abbeel
...
Juil Sock
Stuart J. Russell
Daniel Kahneman
J. Brauner
Sören Mindermann
351
30
0
26 Oct 2023
On existence, uniqueness and scalability of adversarial robustness measures for AI classifiers
I. Horenko
AAML
204
3
0
19 Oct 2023
Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling
International Joint Conference on Artificial Intelligence (IJCAI), 2023
Zun Li
Marc Lanctot
Kevin R. McKee
Luke Marris
I. Gemp
Daniel Hennes
Paul Muller
Kate Larson
Yoram Bachrach
Michael P. Wellman
311
11
0
01 Feb 2023
Impartial Games: A Challenge for Reinforcement Learning
Bei Zhou
Søren Riis
367
6
0
25 May 2022
1
Page 1 of 1
