English
Related papers

Related papers: Provably efficient RL with Rich Observations via L…

200 papers

The low rank MDP has emerged as an important model for studying representation learning and exploration in reinforcement learning. With a known representation, several model-free exploration strategies exist. In contrast, all algorithms for…

Machine Learning · Computer Science 2022-06-23 Aditya Modi , Jinglin Chen , Akshay Krishnamurthy , Nan Jiang , Alekh Agarwal

Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs. We consider here a scenario where the learning agent has the ability to collect online experiences through direct…

Machine Learning · Computer Science 2021-06-29 Maxime Gasse , Damien Grasset , Guillaume Gaudron , Pierre-Yves Oudeyer

We consider a discounted infinite horizon optimal stopping problem. If the underlying distribution is known a priori, the solution of this problem is obtained via dynamic programming (DP) and is given by a well known threshold rule. When…

Machine Learning · Computer Science 2021-02-23 Daniel Russo , Assaf Zeevi , Tianyi Zhang

We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process…

Machine Learning · Computer Science 2026-02-04 Seiji Shaw , Travis Manderson , Chad Kessens , Nicholas Roy

Reinforcement learning (RL) has emerged as a powerful method for improving the reasoning abilities of large language models (LLMs). Outcome-based RL, which rewards policies solely for the correctness of the final answer, yields substantial…

Machine Learning · Computer Science 2025-09-09 Yuda Song , Julia Kempe , Remi Munos

Model-based methods have recently shown great potential for off-policy evaluation (OPE); offline trajectories induced by behavioral policies are fitted to transitions of Markov decision processes (MDPs), which are used to rollout simulated…

Machine Learning · Computer Science 2023-02-06 Qitong Gao , Ge Gao , Min Chi , Miroslav Pajic

Deep RL approaches build much of their success on the ability of the deep neural network to generate useful internal representations. Nevertheless, they suffer from a high sample-complexity and starting with a good input representation can…

Machine Learning · Computer Science 2021-02-17 Vikram Waradpande , Daniel Kudenko , Megha Khosla

Partial observability is a common challenge in many reinforcement learning applications, which requires an agent to maintain memory, infer latent states, and integrate this past information into exploration. This challenge leads to a number…

Machine Learning · Computer Science 2020-10-27 Chi Jin , Sham M. Kakade , Akshay Krishnamurthy , Qinghua Liu

Exploration capacity shapes both inference-time performance and reinforcement learning (RL) training for large (vision-) language models, as stochastic sampling often yields redundant reasoning paths with little high-level diversity. This…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Rujiao Long , Yang Li , Xingyao Zhang , Weixun Wang , Tianqianjin Lin , Xi Zhao , Yuchi Xu , Wenbo Su , Junchi Yan , Bo Zheng

Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. In previous work, to work…

Machine Learning · Computer Science 2024-08-27 Risto Vuorio , Pim de Haan , Johann Brehmer , Hanno Ackermann , Daniel Dijkman , Taco Cohen

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration…

Machine Learning · Computer Science 2024-11-12 Simone Parisi , Alireza Kazemipour , Michael Bowling

Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on complex tasks. However,…

Machine Learning · Computer Science 2022-09-01 Marco Bagatella , Sammy Christen , Otmar Hilliges

The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient…

Machine Learning · Computer Science 2025-12-09 Caleb Ju , Guanghui Lan

While many real-world problems that might benefit from reinforcement learning, these problems rarely fit into the MDP mold: interacting with the environment is often expensive and specifying reward functions is challenging. Motivated by…

Machine Learning · Computer Science 2023-07-26 Kyle Hatch , Benjamin Eysenbach , Rafael Rafailov , Tianhe Yu , Ruslan Salakhutdinov , Sergey Levine , Chelsea Finn

We propose Deterministic Sequencing of Exploration and Exploitation (DSEE) algorithm with interleaving exploration and exploitation epochs for model-based RL problems that aim to simultaneously learn the system model, i.e., a Markov…

Machine Learning · Computer Science 2022-12-21 Piyush Gupta , Vaibhav Srivastava

Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time compute. In this paper, we present a framework for…

Artificial Intelligence · Computer Science 2026-05-06 Ifdita Hasan Orney , Jubayer Ibn Hamid , Shreya S Ramanujam , Shirley Wu , Hengyuan Hu , Noah Goodman , Dorsa Sadigh , Chelsea Finn

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal…

Machine Learning · Computer Science 2018-02-27 Ashvin Nair , Bob McGrew , Marcin Andrychowicz , Wojciech Zaremba , Pieter Abbeel

We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state. We propose a natural data-driven framework, where the system's dynamics are modelled…

Systems and Control · Computer Science 2019-03-01 Ibrahim Ayed , Emmanuel de Bézenac , Arthur Pajot , Julien Brajard , Patrick Gallinari

In real-world reinforcement learning (RL) systems, various forms of {\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe the most recent state of the system due to latency or lossy…

Machine Learning · Computer Science 2023-10-30 Minshuo Chen , Jie Meng , Yu Bai , Yinyu Ye , H. Vincent Poor , Mengdi Wang

We propose a method for learning dynamical systems from high-dimensional empirical data that combines variational autoencoders and (spatio-)temporal attention within a framework designed to enforce certain scientifically-motivated…

Machine Learning · Computer Science 2023-06-22 Kai Lagemann , Christian Lagemann , Sach Mukherjee