English
Related papers

Related papers: Imperfect World Models are Exploitable

200 papers

Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinforcement learning updates in language models and argue that…

Machine Learning · Computer Science 2026-05-26 Wenlong Deng , Jiaji Huang , Kaan Ozkara , Yushu Li , Christos Thrampoulidis , Xiaoxiao Li , Youngsuk Park

We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitation. Particularly,…

Machine Learning · Computer Science 2026-01-23 Ofir Nabati , Guy Tennenholtz , Shie Mannor

Prior work has proposed a simple strategy for reinforcement learning (RL): label experience with the outcomes achieved in that experience, and then imitate the relabeled experience. These outcome-conditioned imitation learning methods are…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Soumith Udatha , Sergey Levine , Ruslan Salakhutdinov

We consider a sequence of repeated interactions between an agent and an environment. Uncertainty about the environment is captured by a probability distribution over a space of hypotheses, which includes all computable functions. Given a…

Artificial Intelligence · Computer Science 2009-12-02 Peter de Blanc

Recommendation systems often face exploration-exploitation tradeoffs: the system can only learn about the desirability of new options by recommending them to some user. Such systems can thus be modeled as multi-armed bandit settings;…

Computer Science and Game Theory · Computer Science 2020-07-02 Gal Bahar , Omer Ben-Porat , Kevin Leyton-Brown , Moshe Tennenholtz

World models - learned internal simulators of environment dynamics - are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. By predicting future states in compressed latent spaces,…

Cryptography and Security · Computer Science 2026-04-08 Manoj Parmar

Learning-based controllers are often purposefully kept out of real-world applications due to concerns about their safety and reliability. We explore how state-of-the-art world models in Model-Based Reinforcement Learning can be utilized…

Robotics · Computer Science 2025-03-05 Fabian Domberg , Georg Schildbach

As machine learning models are increasingly used in critical decision-making settings (e.g., healthcare, finance), there has been a growing emphasis on developing methods to explain model predictions. Such \textit{explanations} are used to…

Machine Learning · Computer Science 2021-06-29 Dylan Slack , Sophie Hilgard , Sameer Singh , Himabindu Lakkaraju

It has been a long-standing dream to design artificial agents that explore their environment efficiently via intrinsic motivation, similar to how children perform curious free play. Despite recent advances in intrinsically motivated…

Machine Learning · Computer Science 2022-11-29 Cansu Sancaktar , Sebastian Blaes , Georg Martius

We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…

Machine Learning · Computer Science 2019-06-10 Ruohan Wang , Carlo Ciliberto , Pierluigi Amadori , Yiannis Demiris

The inherent trade-off in on-line learning is between exploration and exploitation. A good balance between these two (conflicting) goals can achieve a better long-term performance. Can we define an optimal balance? We propose to study this…

Information Theory · Computer Science 2024-11-06 Ram Zamir , Kenneth Rose

We propose a set of precise criteria for saying a neural net learns and uses a "world model." The goal is to give an operational meaning to terms that are often used informally, in order to provide a common language for experimental…

Artificial Intelligence · Computer Science 2025-07-30 Kenneth Li , Fernanda Viégas , Martin Wattenberg

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…

Machine Learning · Computer Science 2020-01-01 Aviral Kumar , Xue Bin Peng , Sergey Levine

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

Computation and Language · Computer Science 2025-07-16 Pedro Ferreira , Wilker Aziz , Ivan Titov

Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gather valuable information about the state of the world for…

Machine Learning · Computer Science 2020-11-03 Haiyan Yin , Yingzhen Li , Sinno Jialin Pan , Cheng Zhang , Sebastian Tschiatschek

Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for such learning…

Machine Learning · Statistics 2018-08-10 Iñigo Urteaga , Chris H. Wiggins

While data-driven predictive models are a strictly technological construct, they may operate within a social context in which benign engineering choices entail implicit, indirect and unexpected real-life consequences. Fairness of such…

Machine Learning · Computer Science 2024-07-11 Kacper Sokol , Meelis Kull , Jeffrey Chan , Flora Salim

Full models of the world require complex knowledge of immense detail. While pre-trained large models have been hypothesized to contain similar knowledge due to extensive pre-training on vast amounts of internet scale data, using them…

Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding needs further studies. In this paper, we firstly analyze…

Machine Learning · Computer Science 2020-10-23 Tian Xu , Ziniu Li , Yang Yu

We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the open-endedness of living things, we start from the…

Neural and Evolutionary Computing · Computer Science 2024-11-20 Kazuya Horibe , Naoto Yoshida
‹ Prev 1 3 4 5 6 7 10 Next ›