English
Related papers

Related papers: SafeLife 1.0: Exploring Side Effects in Complex En…

200 papers

Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying…

Artificial Intelligence · Computer Science 2017-12-11 Alexander Peysakhovich , Adam Lerer

Obtaining safety guarantees for reinforcement learning is a major challenge to achieve applicability for real-world tasks. Safety shields extend standard reinforcement learning and achieve hard safety guarantees. However, existing safety…

Machine Learning · Computer Science 2025-11-27 Jin Pin , Krasowski Hanna , Vanneaux Elena

We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things…

Artificial Intelligence · Computer Science 2022-07-21 Samuel Allen Alexander , Michael Castaneda , Kevin Compher , Oscar Martinez

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult…

Machine Learning · Computer Science 2014-11-03 Aaron Defazio , Thore Graepel

The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches,…

Systems and Control · Electrical Eng. & Systems 2024-07-02 Peipei Yu , Zhenyi Wang , Hongcai Zhang , Yonghua Song

Reinforcement Learning (RL), a subfield of Artificial Intelligence (AI), focuses on training agents to make decisions by interacting with their environment to maximize cumulative rewards. This paper provides an overview of RL, covering its…

Artificial Intelligence · Computer Science 2024-12-04 Majid Ghasemi , Dariush Ebrahimi

Cyber-Physical Systems (CPS) often leverage Reinforcement Learning (RL) techniques to adapt dynamically to changing environments and optimize performance. However, it is challenging to construct safety cases for RL components. We therefore…

Software Engineering · Computer Science 2025-03-13 Katherine Dearstyne , Pedro , Alarcon Granadeno , Theodore Chambers , Jane Cleland-Huang

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior…

Machine Learning · Computer Science 2021-04-20 Md Sultan Al Nahian , Spencer Frazier , Brent Harrison , Mark Riedl

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or…

Machine Learning · Computer Science 2025-03-21 Claire Chen , Shuze Daniel Liu , Shangtong Zhang

The performance of reinforcement learning depends upon designing an appropriate action space, where the effect of each action is measurable, yet, granular enough to permit flexible behavior. So far, this process involved non-trivial user…

Machine Learning · Computer Science 2021-06-08 Edoardo Cetin , Oya Celiktutan

Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can entail additional costs and safety risks, the common paradigm of sim2real conducts…

Artificial Intelligence · Computer Science 2023-12-11 Minqi Jiang

Game environments offer a unique opportunity for training virtual agents due to their interactive nature, which provides diverse play traces and affect labels. Despite their potential, no reinforcement learning framework incorporates human…

Artificial Intelligence · Computer Science 2024-07-29 Matthew Barthet , Roberto Gallotta , Ahmed Khalifa , Antonios Liapis , Georgios N. Yannakakis

The world currently offers an abundance of data in multiple domains, from which we can learn reinforcement learning (RL) policies without further interaction with the environment. RL agents learning offline from such data is possible but…

Machine Learning · Computer Science 2022-12-19 Hager Radi , Josiah P. Hanna , Peter Stone , Matthew E. Taylor

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm…

Offline safe reinforcement learning (RL) has emerged as a promising approach for learning safe behaviors without engaging in risky online interactions with the environment. Most existing methods in offline safe RL rely on cost constraints…

Machine Learning · Computer Science 2025-04-22 Ze Gong , Akshat Kumar , Pradeep Varakantham

We develop a framework for interacting with uncertain environments in reinforcement learning (RL) by leveraging preferences in the form of utility functions. We claim that there is value in considering different risk measures during…

Machine Learning · Computer Science 2021-02-23 Hannes Eriksson , Christos Dimitrakakis

Agents should avoid unsafe behaviour during both training and deployment. This typically requires a simulator and a procedural specification of unsafe behaviour. Unfortunately, a simulator is not always available, and procedurally…

Machine Learning · Computer Science 2022-01-24 Matthew Rahtz , Vikrant Varma , Ramana Kumar , Zachary Kenton , Shane Legg , Jan Leike

Vanilla Reinforcement Learning (RL) can efficiently solve complex tasks but does not provide any guarantees on system behavior. To bridge this gap, we propose a three-step safe RL procedure for continuous action spaces that provides…

Robotics · Computer Science 2023-09-29 Hanna Krasowski , Prithvi Akella , Aaron D. Ames , Matthias Althoff

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that…

Computation and Language · Computer Science 2026-02-05 Zhexin Zhang , Yida Lu , Junfeng Fang , Junxiao Yang , Shiyao Cui , Hao Zhou , Fandong Meng , Jie Zhou , Hongning Wang , Minlie Huang , Tat-Seng Chua

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact.…

Machine Learning · Computer Science 2026-04-06 André Biedenkapp