Are Alphazero-like Agents Robust To Adversarial Perturbations?

Abstract

The success of AlphaZero (AZ) has demonstrated that neural-network-based Go AIs can surpass human performance by a large margin. Given that the state space of Go is extremely large and a human player can play the game from any legal state, we ask whether adversarial states exist for Go AIs that may lead them to play surprisingly wrong actions. In this paper, we first extend the concept of adversarial examples to the game of Go: we generate perturbed states that are ``semantically'' equivalent to the original state by adding meaningless moves to the game, and an adversarial state is a perturbed state leading to an undoubtedly inferior action that is obvious even for Go beginners. However, searching the adversarial state is challenging due to the large, discrete, and non-differentiable search space. To tackle this challenge, we develop the first adversarial attack on Go AIs that can efficiently search for adversarial states by strategically reducing the search space. This method can also

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylan2022are

Related papers

• Targeted Search Control In Alphazero For Effective Policy Improvement (2023)0.00
• Approximate Exploitability: Learning A Best Response In Large Games (2020)0.00
• ELF Opengo: An Analysis And Open Reimplementation Of Alphazero (2019)0.00
• Impartial Games: A Challenge For Reinforcement Learning (2022)0.00
• Regret-guided Search Control For Efficient Learning In Alphazero (2026)0.00
• Policy-value Alignment And Robustness In Search-based Multi-agent Learning (2023)0.00
• The Entropy Of Artificial Intelligence And A Case Study Of Alphazero From Shannon's Perspective (2018)0.00
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00