English
Related papers

Related papers: Pessimism About Unknown Unknowns Inspires Conserva…

200 papers

We study worst-case guarantees on the expected return of fixed-dataset policy optimization algorithms. Our core contribution is a unified conceptual and mathematical framework for the study of algorithms in this regime. This analysis…

Artificial Intelligence · Computer Science 2020-12-01 Jacob Buckman , Carles Gelada , Marc G. Bellemare

Reinforcement learners are agents that learn to pick actions that lead to high reward. Ideally, the value of a reinforcement learner's policy approaches optimality--where the optimal informed policy is the one which maximizes reward.…

Machine Learning · Computer Science 2021-05-27 Michael K. Cohen , Elliot Catt , Marcus Hutter

Reinforcement Learning agents are expected to eventually perform well. Typically, this takes the form of a guarantee about the asymptotic behavior of an algorithm given some assumptions about the environment. We present an algorithm for a…

Machine Learning · Computer Science 2020-04-02 Michael K. Cohen , Elliot Catt , Marcus Hutter

As artificial agents become increasingly capable, what internal structure is *necessary* for an agent to act competently under uncertainty? Classical results show that optimal control can be *implemented* using belief states or world…

Machine Learning · Computer Science 2026-04-03 Aran Nayebi

Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand the agent's subjective reward range to include a large negative value $-L$, while the true…

Machine Learning · Computer Science 2026-04-16 Aram Ebtekar , Michael K. Cohen

When subjected to automated decision-making, decision subjects may strategically modify their observable features in ways they believe will maximize their chances of receiving a favorable decision. In many practical situations, the…

Computer Science and Game Theory · Computer Science 2022-10-10 Keegan Harris , Valerie Chen , Joon Sik Kim , Ameet Talwalkar , Hoda Heidari , Zhiwei Steven Wu

Methods for learning optimal policies in autonomous agents often assume that the way the domain is conceptualised---its possible states and actions and their causal structure---is known in advance and does not change during learning. This…

Artificial Intelligence · Computer Science 2018-01-11 Craig Innes , Alex Lascarides , Stefano V Albrecht , Subramanian Ramamoorthy , Benjamin Rosman

In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improved performance is the use of pessimistic value updates to…

Machine Learning · Computer Science 2022-04-07 Ted Moskovitz , Jack Parker-Holder , Aldo Pacchiano , Michael Arbel , Michael I. Jordan

The ideal Bayesian agent reasons from a global probability model, but real agents are restricted to simplified models which they know to be adequate only in restricted circumstances. Very little formal theory has been developed to help…

Artificial Intelligence · Computer Science 2013-03-25 Kathryn Blackmond Laskey

In cooperative multiagent planning, it can often be beneficial for an agent to make commitments about aspects of its behavior to others, allowing them in turn to plan their own behaviors without taking the agent's detailed behavior into…

Artificial Intelligence · Computer Science 2017-03-16 Qi Zhang , Satinder Singh , Edmund Durfee

The well-worn George Box aphorism ``all models are wrong, but some are useful'' is particularly salient in the cybersecurity domain, where the assumptions built into a model can have substantial financial or even national security impacts.…

Cryptography and Security · Computer Science 2025-06-17 Erick Galinkin , Emmanouil Pountourakis , Spiros Mancoridis

Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we…

Machine Learning · Computer Science 2024-06-03 Hao Hu , Yiqin Yang , Jianing Ye , Chengjie Wu , Ziqing Mai , Yujing Hu , Tangjie Lv , Changjie Fan , Qianchuan Zhao , Chongjie Zhang

Optimization of complex functions, such as the output of computer simulators, is a difficult task that has received much attention in the literature. A less studied problem is that of optimization under unknown constraints, i.e., when the…

Methodology · Statistics 2010-07-06 Robert B. Gramacy , Herbert K. H. Lee

We study a dynamic model of Bayesian persuasion in sequential decision-making settings. An informed principal observes an external parameter of the world and advises an uninformed agent about actions to take over time. The agent takes…

Computer Science and Game Theory · Computer Science 2022-05-25 Jiarui Gan , Rupak Majumdar , Goran Radanovic , Adish Singla

We consider an agent who represents uncertainty about the environment via a possibly misspecified model. Each period, the agent takes an action, observes a consequence, and uses Bayes' rule to update her belief about the environment. This…

Theoretical Economics · Economics 2019-10-24 Ignacio Esponda , Demian Pouzo , Yuichi Yamamoto

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Computer Science 2014-08-12 Aristide Tossou , Christos Dimitrakakis

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Statistics 2013-07-16 Aristide C. Y. Tossou , Christos Dimitrakakis

Meta-training agents with memory has been shown to culminate in Bayes-optimal agents, which casts Bayes-optimality as the implicit solution to a numerical optimization problem rather than an explicit modeling assumption. Bayes-optimal…

This paper studies how uncertainty about problem difficulty shapes problem-solving strategies. I develop a dynamic model where an agent solves a problem by brainstorming approaches of unknown quality and allocating a fixed effort budget…

Theoretical Economics · Economics 2026-04-02 Nicholas Wu

We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic…

Artificial Intelligence · Computer Science 2013-05-17 Peter Sunehag , Marcus Hutter
‹ Prev 1 2 3 10 Next ›