English
Related papers

Related papers: Learning a Shield from Catastrophic Action Effects…

200 papers

We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations…

Machine Learning · Computer Science 2013-03-19 Odalric-Ambrym Maillard , Phuong Nguyen , Ronald Ortner , Daniil Ryabko

Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy…

Machine Learning · Computer Science 2018-04-20 Gang Chen , Yiming Peng , Mengjie Zhang

Direct Preference Optimisation (DPO) is widely used for safety alignment in large language models. However, prior work shows it is brittle and exhibits poor out-of-distribution (OOD) generalisation. In this paper, we investigate whether…

Machine Learning · Computer Science 2026-05-27 Sandeep Kumar , Virginia Smith , Chhavi Yadav

Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired knowledge or…

Machine Learning · Computer Science 2023-12-04 Nuri Korhan , Ceren Öner

This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. Motivated by…

Machine Learning · Computer Science 2023-07-07 Jiacheng Guo , Minshuo Chen , Huan Wang , Caiming Xiong , Mengdi Wang , Yu Bai

This paper proposes a framework for safe reinforcement learning that can handle stochastic nonlinear dynamical systems. We focus on the setting where the nominal dynamics are known, and are subject to additive stochastic disturbances with…

Systems and Control · Electrical Eng. & Systems 2020-01-27 Shuo Li , Osbert Bastani

To be helpful assistants, AI agents must be aware of their own capabilities and limitations. This includes knowing when to answer from parametric knowledge versus using tools, when to trust tool outputs, and when to abstain or hedge. Such…

Machine Learning · Computer Science 2025-09-01 Jacob Eisenstein , Reza Aghajani , Adam Fisch , Dheeru Dua , Fantine Huot , Mirella Lapata , Vicky Zayats , Jonathan Berant

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Machine Learning · Computer Science 2020-12-16 Eden Belouadah , Adrian Popescu , Ioannis Kanellos

We propose a decision-theoretic framework in which a robot strategically can shape inferred human's prosocial state during repeated interactions. Modeling the human's prosociality as a latent state that evolves over time, the robot learns…

Human-Computer Interaction · Computer Science 2026-03-04 Zahra Zahedi , Xinyue Hu , Shashank Mehrotra , Mark Steyvers , Kumar Akash

Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the lack of formal safety guarantees still limits its application in safety-critical settings. A common practical approach is to augment the RL…

Machine Learning · Computer Science 2026-02-12 Donggeon David Oh , Duy P. Nguyen , Haimin Hu , Jaime F. Fisac

Cooperative multi-agent reinforcement learning (MARL) is typically formalised as a Decentralised Partially Observable Markov Decision Process (Dec-POMDP), where agents must reason about the environment and other agents' behaviour. In…

Machine Learning · Computer Science 2025-07-25 Kale-ab Abebe Tessera , Leonard Hinckeldey , Riccardo Zamboni , David Abel , Amos Storkey

Our goal is to model and experimentally assess trust evolution to predict future beliefs and behaviors of human-robot teams in dynamic environments. Research suggests that maintaining trust among team members in a human-robot team is vital…

Robotics · Computer Science 2025-11-12 Dong Hae Mangalindan , Ericka Rovira , Vaibhav Srivastava

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…

Machine Learning · Computer Science 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

In high-stakes AI applications, even a single action can cause irreparable damage. However, nearly all of sequential decision-making theory assumes that all errors are recoverable (e.g., by bounding rewards). Standard bandit algorithms that…

Machine Learning · Computer Science 2026-04-14 Sarah Liaw , Benjamin Plaut

This paper extends the framework of partially observable Markov decision processes (POMDPs) to multi-agent settings by incorporating the notion of agent models into the state space. Agents maintain beliefs over physical states of the…

Artificial Intelligence · Computer Science 2011-09-13 P. Doshi , P. J. Gmytrasiewicz

In this paper we propose a method that learns to play Pac-Man. We define a set of high-level observation and action modules. Actions are temporally extended, and multiple action modules may be in effect concurrently. A decision of the agent…

Machine Learning · Computer Science 2007-05-23 Istvan Szita , Andras Lorincz

In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobserved factors, inducing confounding and biasing estimates…

Machine Learning · Computer Science 2023-03-24 Andrew Bennett , Nathan Kallus

This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large…

Machine Learning · Computer Science 2019-11-26 Guy Tennenholtz , Shie Mannor , Uri Shalit

Humans learn from catastrophic mistakes not through numerical penalties, but through qualitative suffering that reshapes who they are. Current AI safety approaches replicate none of this. Reward shaping captures magnitude, not meaning.…

Artificial Intelligence · Computer Science 2026-03-17 Pandurang Mopgar

Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining…

Artificial Intelligence · Computer Science 2017-09-13 Denis Steckelmacher , Diederik M. Roijers , Anna Harutyunyan , Peter Vrancx , Hélène Plisnier , Ann Nowé