English
Related papers

Related papers: CAMPs: Learning Context-Specific Abstractions for …

200 papers

While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e.g., environments, obstacles,…

Machine Learning · Computer Science 2021-09-06 Xiaowu Sun , Wael Fatnassi , Ulices Santa Cruz , Yasser Shoukry

Generalized planning is concerned with the computation of plans that solve not one but multiple instances of a planning domain. Recently, it has been shown that generalized plans can be expressed as mappings of feature values into actions,…

Artificial Intelligence · Computer Science 2018-11-20 Blai Bonet , Guillem Francès , Hector Geffner

Accomplishing household tasks requires to plan step-by-step actions considering the consequences of previous actions. However, the state-of-the-art embodied agents often make mistakes in navigating the environment and interacting with…

Robotics · Computer Science 2024-03-14 Byeonghwi Kim , Jinyeon Kim , Yuyeong Kim , Cheolhong Min , Jonghyun Choi

Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over single agent systems, they lead to huge computational overheads because of heavy…

Multiagent Systems · Computer Science 2026-05-29 Ziyang Ma , Dingyi Zhang , Sichu Liang , Jiajia Chu , Pengfei Xia , Hui Zang , Deyu Zhou

Often times, we specify tasks for a robot using temporal language that can also span different levels of abstraction. The example command ``go to the kitchen before going to the second floor'' contains spatial abstraction, given that…

Robotics · Computer Science 2019-05-30 Yoonseon Oh , Roma Patel , Thao Nguyen , Baichuan Huang , Ellie Pavlick , Stefanie Tellex

Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement learning problems. However, the properties of meta-gradients…

Machine Learning · Computer Science 2022-09-14 Jelena Luketina , Sebastian Flennerhag , Yannick Schroecker , David Abel , Tom Zahavy , Satinder Singh

We consider the problem of controlling a fully specified Markov decision process (MDP), also known as the planning problem, when the state space is very large and calculating the optimal policy is intractable. Instead, we pursue the more…

Optimization and Control · Mathematics 2019-01-09 Yasin Abbasi-Yadkori , Peter L. Bartlett , Xi Chen , Alan Malek

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…

Machine Learning · Computer Science 2019-10-23 Jan Humplik , Alexandre Galashov , Leonard Hasenclever , Pedro A. Ortega , Yee Whye Teh , Nicolas Heess

Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes…

Machine Learning · Computer Science 2021-05-21 Lucas N. Alegre , Ana L. C. Bazzan , Bruno C. da Silva

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Machine Learning · Computer Science 2021-03-31 Giulia Denevi , Massimiliano Pontil , Carlo Ciliberto

The paper considers a class of multi-agent Markov decision processes (MDPs), in which the network agents respond differently (as manifested by the instantaneous one-stage random costs) to a global controlled state and the control actions of…

Machine Learning · Statistics 2015-06-04 Soummya Kar , Jose' M. F. Moura , H. Vincent Poor

We present a methodology for formulating simplifying abstractions in machine learning systems by identifying and harnessing the utility structure of decisions. Machine learning tasks commonly involve high-dimensional output spaces (e.g.,…

Machine Learning · Computer Science 2023-03-31 Michael Poli , Stefano Massaroli , Stefano Ermon , Bryan Wilder , Eric Horvitz

In this semi-tutorial paper, we first review the information-theoretic approach to account for the computational costs incurred during the search for optimal actions in a sequential decision-making problem. The traditional (MDP) framework…

Artificial Intelligence · Computer Science 2021-02-23 Daniel T. Larsson , Daniel Braun , Panagiotis Tsiotras

Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been…

Machine Learning · Computer Science 2026-05-22 Clarisse Wibault , Alexander Goldie , Antonio Villares , Maike Osborne , Jakob Foerster

Dropped into an unknown environment, what should an agent do to quickly learn about the environment and how to accomplish diverse tasks within it? We address this question within the goal-conditioned reinforcement learning paradigm, by…

Machine Learning · Computer Science 2023-03-24 Edward S. Hu , Richard Chang , Oleh Rybkin , Dinesh Jayaraman

Task And Motion Planning (TAMP) is the problem of finding a solution to an automated planning problem that includes discrete actions executable by low-level continuous motions. This field is gaining increasing interest within the robotics…

Robotics · Computer Science 2024-08-13 Elisa Tosello , Alessandro Valentini , Andrea Micheli

Policy-based algorithms are among the most widely adopted techniques in model-free RL, thanks to their strong theoretical groundings and good properties in continuous action spaces. Unfortunately, these methods require precise and…

Machine Learning · Computer Science 2023-06-14 Luca Sabbioni , Francesco Corda , Marcello Restelli

Contextual multi-armed bandits are a popular choice to model sequential decision-making. E.g., in a healthcare application we may perform various tests to asses a patient condition (exploration) and then decide on the best treatment to give…

Machine Learning · Computer Science 2025-04-08 Mirco Mutti , Jeongyeol Kwon , Shie Mannor , Aviv Tamar

In many sequential decision-making problems, the goal is to optimize a utility function while satisfying a set of constraints on different utilities. This learning problem is formalized through Constrained Markov Decision Processes (CMDPs).…

Machine Learning · Computer Science 2020-03-05 Yonathan Efroni , Shie Mannor , Matteo Pirotta

We study off-policy evaluation and learning from sequential data in a structured class of Markov decision processes that arise from repeated interactions with an exogenous sequence of arrivals with contexts, which generate unknown…

Machine Learning · Computer Science 2021-10-20 Nathan Kallus , Angela Zhou