paper-with-me

홈 › Papers

Shielding Atari Games with Bounded Prescience

2021-01-20 · Mirco Giacobbe, Mohammadhosein Hasanbeig, Daniel Kroening, Hjalmar Wijk

Deep reinforcement learning (DRL) is applied in safety-critical domains such as robotics and autonomous driving. It achieves superhuman abilities in many tasks, however whether DRL agents can be shown to act safely is an open problem. Atari games are a simple yet challenging exemplar for evaluating the safety of DRL agents and feature a diverse portfolio of game mechanics. The safety of neural agents has been studied before using methods that either require a model of the system dynamics or an abstraction; unfortunately, these are unsuitable to Atari games because their low-level dynamics are complex and hidden inside their emulator. We present the first exact method for analysing and ensuring the safety of DRL agents for Atari games. Our method only requires access to the emulator. First, we give a set of 43 properties that characterise "safe behaviour" for 30 games. Second, we develop a method for exploring all traces induced by an agent and a game and consider a variety of sources of game non-determinism. We observe that the best available DRL agents reliably satisfy only very few properties; several critical properties are violated by all agents. Finally, we propose a countermeasure that combines a bounded explicit-state exploration with shielding. We demonstrate that our method improves the safety of all agents over multiple properties.

📄 PDF Abstract BibTeX arXiv:2101.08153

Code (1)

HjalmarWijk/bounded-prescience 공식 구현 tf

Tasks

Atari GamesAutonomous DrivingDeep Reinforcement Learning

Similar Papers 제목 키워드 기반

Approximate Shielding of Atari Agents for Safe Exploration

2023-04-21 · Alexander W. Goodall, Francesco Belardinelli

Balancing exploration and conservatism in the constrained setting is an important problem if we are to use reinforcement learning for meaningful tasks in the real world. In this paper, we propose a principled algorithm f…

Atari GamesSafe Exploration

Approximate Model-Based Shielding for Safe Reinforcement Learning

2023-07-27 · Alexander W. Goodall, Francesco Belardinelli

Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to safety-critical systems in the real-world is not easy as many algorithms are sample-ineffic…

Atari Gamesmodelreinforcement-learningReinforcement Learning+2

PreScience: A Dataset and Benchmark for Scientific Forecasting

2026-02-24 · Anirudh Ajith, Amanpreet Singh, Jay DeYoung, Nadav Kunievsky 외 arxiv

Can AI systems trained on the existing scientific record forecast the advances that will follow? We introduce PreScience, a dataset and benchmark for scientific forecasting built around 98K recent AI research papers, tog…

Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning

2025-11-04 · Tiberiu-Andrei Georgescu, Alexander W. Goodall, Dalal Alrajeh, Francesco Belardinelli 외 arxiv

Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the s…

Inductive logic programmingReinforcement Learning

Model-Based Reinforcement Learning for Atari

2019-03-01 · Lukasz Kaiser, Mohammad Babaeizadeh, Piotr Milos, Blazej Osinski 외

Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- s…

Atari GamesAtari Games 100kmodelModel-based Reinforcement Learning+4