English
Related papers

Related papers: Learning How to Infer Partial MDPs for In-Context …

200 papers

Contextual policy search allows adapting robotic movement primitives to different situations. For instance, a locomotion primitive might be adapted to different terrain inclinations or desired walking speeds. Such an adaptation is often…

Machine Learning · Statistics 2015-11-17 Jan Hendrik Metzen

Partially Observable Markov Decision Processes (POMDPs) remain a core challenge in reinforcement learning due to incomplete state information. We address this by reformulating POMDPs as fully observable processes with fixed-length…

Machine Learning · Computer Science 2025-09-16 Wuhao Wang , Zhiyong Chen

We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which…

Partially Observable Markov Decision Processes (POMDPs) model decision making under uncertainty. While there are many approaches to approximately solving POMDPs, we aim to address the problem of learning such models. In particular, we are…

Artificial Intelligence · Computer Science 2025-05-13 Aidan Curtis , Hao Tang , Thiago Veloso , Kevin Ellis , Joshua Tenenbaum , Tomás Lozano-Pérez , Leslie Pack Kaelbling

We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied…

Computation and Language · Computer Science 2026-02-26 Eric Todd , Jannik Brinkmann , Rohit Gandikota , David Bau

Partially observable Markov decision processes (POMDPs) are a powerful abstraction for tasks that require decision making under uncertainty, and capture a wide range of real world tasks. Today, effective planning approaches exist that…

Machine Learning · Statistics 2018-05-24 Sebastian Tschiatschek , Kai Arulkumaran , Jan Stühmer , Katja Hofmann

In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are…

Machine Learning · Computer Science 2025-05-19 Ashok Arora , Neetesh Kumar

Partially observable Markov decision processes (POMDPs) are a natural model for planning problems where effects of actions are nondeterministic and the state of the world is not completely observable. It is difficult to solve POMDPs…

Artificial Intelligence · Computer Science 2009-09-25 N. L. Zhang , W. Liu

Contextual bandits constitute a classical framework for decision-making under uncertainty. In this setting, the goal is to learn the arms of highest reward subject to contextual information, while the unknown reward parameters of each arm…

Machine Learning · Statistics 2024-02-19 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP).…

Machine Learning · Computer Science 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

Recently, it has been shown how sampling actions from the predictive distribution over the optimal action-sometimes called Thompson sampling-can be applied to solve sequential adaptive control problems, when the optimal policy is known for…

Artificial Intelligence · Computer Science 2014-09-24 Pedro A. Ortega , Daniel A. Braun

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

Learning-based approaches to robotic manipulation are limited by the scalability of data collection and accessibility of labels. In this paper, we present a multi-task domain adaptation framework for instance grasping in cluttered scenes by…

Machine Learning · Computer Science 2018-03-06 Kuan Fang , Yunfei Bai , Stefan Hinterstoisser , Silvio Savarese , Mrinal Kalakrishnan

Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration and adaptation, often…

Machine Learning · Computer Science 2025-07-15 Andrew Wagenmaker , Zhiyuan Zhou , Sergey Levine

Faced with an ever-increasing complexity of their domains of application, artificial learning agents are now able to scale up in their ability to process an overwhelming amount of information coming from their interaction with an…

Artificial Intelligence · Computer Science 2022-04-05 Mirza Ramicic , Andrea Bonarini

Contextual Markov decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. While CMDPs serve…

Machine Learning · Computer Science 2024-02-06 Junze Deng , Yuan Cheng , Shaofeng Zou , Yingbin Liang

General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes…

Artificial Intelligence · Computer Science 2009-12-30 Marcus Hutter

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not…

Artificial Intelligence · Computer Science 2016-12-04 Sai Praveen Bangaru , JS Suhas , Balaraman Ravindran

In many biomedical, science, and engineering problems, one must sequentially decide which action to take next so as to maximize rewards. One general class of algorithms for optimizing interactions with the world, while simultaneously…

Machine Learning · Statistics 2021-05-05 Iñigo Urteaga , Chris H. Wiggins