English
Related papers

Related papers: Learning a Shield from Catastrophic Action Effects…

200 papers

Policy search reinforcement learning allows robots to acquire skills by themselves. However, the learning procedure is inherently unsafe as the robot has no a-priori way to predict the consequences of the exploratory actions it takes.…

Robotics · Computer Science 2018-10-09 Jens Lundell , Robert Krug , Erik Schaffernicht , Todor Stoyanov , Ville Kyrki

We consider a two-agent MDP framework where agents repeatedly solve a task in a collaborative setting. We study the problem of designing a learning algorithm for the first agent (A1) that facilitates a successful collaboration even in cases…

Machine Learning · Computer Science 2019-06-21 Goran Radanovic , Rati Devidze , David C. Parkes , Adish Singla

Continual Multi-Agent Reinforcement Learning (Co-MARL) requires agents to address catastrophic forgetting issues while learning new coordination policies with the dynamics team. In this paper, we delve into the core of Co-MARL, namely…

Multiagent Systems · Computer Science 2025-07-09 Chang Yao , Youfang Lin , Shoucheng Song , Hao Wu , Yuqing Ma , Shang Han , Kai Lv

Multi-Agent Reinforcement Learning (MARL) is commonly deployed in settings where agents are trained via self-play with homogeneous teammates, often using parameter sharing and a single policy architecture. This opens the question: to what…

Robotics · Computer Science 2026-03-10 Ryan LeRoy , Jack Kolb

In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training a new model and validating the model. This continual model…

Machine Learning · Computer Science 2025-04-22 Gang Li , Wendi Yu , Yao Yao , Wei Tong , Yingbin Liang , Qihang Lin , Tianbao Yang

It is well known that sequential decision making may lead to information cascades. That is, when agents make decisions based on their private information, as well as observing the actions of those before them, then it might be rational to…

Probability · Mathematics 2018-02-22 Yuval Peres , Miklos Z. Racz , Allan Sly , Izabella Stuhl

Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic…

Machine Learning · Computer Science 2018-09-17 Ignasi Clavera , Jonas Rothfuss , John Schulman , Yasuhiro Fujita , Tamim Asfour , Pieter Abbeel

An AI agent might surprisingly find she has reached an unknown state which she has never been aware of -- an unknown unknown. We mathematically ground this scenario in reinforcement learning: an agent, after taking an action calculated from…

Machine Learning · Computer Science 2025-09-04 Juntian Zhu , Miguel de Carvalho , Zhouwang Yang , Fengxiang He

Reinforcement learning is a proven technique for an agent to learn a task. However, when learning a task using reinforcement learning, the agent cannot distinguish the characteristics of the environment from those of the task. This makes it…

Artificial Intelligence · Computer Science 2017-08-10 Pieter Van Molle , Tim Verbelen , Steven Bohez , Sam Leroux , Pieter Simoens , Bart Dhoedt

Safe reinforcement learning is extremely challenging--not only must the agent explore an unknown environment, it must do so while ensuring no safety constraint violations. We formulate this safe reinforcement learning (RL) problem using the…

Machine Learning · Computer Science 2022-10-19 Archana Bura , Aria HasanzadeZonuzy , Dileep Kalathil , Srinivas Shakkottai , Jean-Francois Chamberland

Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones. Most preference-based safety alignment methods collapse safety into a…

Computation and Language · Computer Science 2026-04-22 Tiankai Yang , Yi Nian , Xinyuan Li , Ruiyao Xu , Kaize Ding , Yue Zhao

Partially Observable Markov Decision Processes (POMDPs) are the standard framework for decision-making under uncertainty. While sampling-based methods scale well, they lack formal correctness guarantees, making them unsuitable for…

Artificial Intelligence · Computer Science 2026-05-15 Debraj Chakraborty , Anirban Majumdar , Prince Mathew , Sayan Mukherjee , Jean-François Raskin

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on…

Machine Learning · Computer Science 2019-10-01 Zhenyu Zhang , Xiangfeng Luo , Tong Liu , Shaorong Xie , Jianshu Wang , Wei Wang , Yang Li , Yan Peng

This paper proposes a reinforcement learning method for controller synthesis of autonomous systems in unknown and partially-observable environments with subjective time-dependent safety constraints. Mathematically, we model the system…

Robotics · Computer Science 2021-04-06 Yu Wang , Alper Kamil Bozkurt , Miroslav Pajic

AI systems are increasingly applied to complex tasks that involve interaction with humans. During training, such systems are potentially dangerous, as they haven't yet learned to avoid actions that could cause serious harm. How can an AI…

Artificial Intelligence · Computer Science 2017-07-18 William Saunders , Girish Sastry , Andreas Stuhlmueller , Owain Evans

Reinforcement learning is generally difficult for partially observable Markov decision processes (POMDPs), which occurs when the agent's observation is partial or noisy. To seek good performance in POMDPs, one strategy is to endow the agent…

Machine Learning · Computer Science 2021-11-19 Mario Geiger , Christophe Eloy , Matthieu Wyart

Learning in POMDPs is known to be significantly harder than in MDPs. In this paper, we consider the online learning problem for episodic POMDPs with unknown transition and observation models. We propose a Posterior Sampling-based…

Machine Learning · Computer Science 2024-10-24 Dengwang Tang , Dongze Ye , Rahul Jain , Ashutosh Nayyar , Pierluigi Nuzzo

Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term…

Artificial Intelligence · Computer Science 2018-02-20 Qingkai Liang , Fanyu Que , Eytan Modiano

The use of reward functions to structure AI learning and decision making is core to the current reinforcement learning paradigm; however, without careful design of reward functions, agents can learn to solve problems in ways that may be…

Artificial Intelligence · Computer Science 2025-01-22 Jonathan Keane , Sam Keyser , Jeremy Kedziora

Warning: This paper contains content that may be inappropriate or offensive. AI agents have gained significant recent attention due to their autonomous tool usage capabilities and their integration in various real-world applications. This…

Artificial Intelligence · Computer Science 2025-06-24 Ninareh Mehrabi , Tharindu Kumarage , Kai-Wei Chang , Aram Galstyan , Rahul Gupta