English
Related papers

Related papers: GLIB: Efficient Exploration for Relational Model-B…

200 papers

Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorithms rely solely on scalar rewards, leaving the rich…

Computation and Language · Computer Science 2026-03-06 Lei Huang , Xiang Cheng , Chenxiao Zhao , Guobin Shen , Junjie Yang , Xiaocheng Feng , Yuxuan Gu , Xing Yu , Bing Qin

With the rapid emergence of multi-behavior learning in recommender systems, leveraging auxiliary user behaviors has proven effective for mitigating target-behavior data sparsity. Yet auxiliary behavior graphs frequently contain noisy or…

Information Retrieval · Computer Science 2026-05-26 Likang Wu , Zihao Chen , Jianxin Zhang , Sangqi Zhu , Yuanyuan Ge , Haipeng Yang , Lei Zhang

Recently, a simple yet effective algorithm -- goal-conditioned supervised-learning (GCSL) -- was proposed to tackle goal-conditioned reinforcement-learning. GCSL is based on the principle of hindsight learning: by observing states visited…

Machine Learning · Computer Science 2023-05-18 Tom Jurgenson , Aviv Tamar

Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents. Large…

Computation and Language · Computer Science 2024-03-06 Hitesh Golchha , Sahil Yerawar , Dhruvesh Patel , Soham Dan , Keerthiram Murugesan

We propose a novel Reinforcement Learning model for discrete environments, which is inherently interpretable and supports the discovery of deep subgoal hierarchies. In the model, an agent learns information about environment in the form of…

Artificial Intelligence · Computer Science 2022-02-16 Alexander Demin , Denis Ponomaryov

Active learning strategies respond to the costly labelling task in a supervised classification by selecting the most useful unlabelled examples in training a predictive model. Many conventional active learning algorithms focus on refining…

Machine Learning · Computer Science 2014-08-12 Djallel Bouneffouf

Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents that need to be carefully selected and tuned. As a result the…

Artificial Intelligence · Computer Science 2021-04-21 Luis Pineda , Brandon Amos , Amy Zhang , Nathan O. Lambert , Roberto Calandra

We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-step process, which starts by mining rules from a deep RL…

Machine Learning · Computer Science 2025-03-13 Martin Tappler , Ignacio D. Lopez-Miguel , Sebastian Tschiatschek , Ezio Bartocci

Models capable of "thinking with images" by dynamically grounding their reasoning in visual evidence represent a major leap in multimodal AI. However, replicating and advancing this ability is non-trivial, with current methods often trapped…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Zhaoyang Wei , Wenchao Ding , Yanchao Hao , Xi Chen

Reinforcement Learning (RL) agents often struggle in sparse-reward environments where traditional exploration strategies fail to discover effective action sequences. Large Language Models (LLMs) possess procedural knowledge and reasoning…

Machine Learning · Computer Science 2025-10-13 Vaibhav Jain , Gerrit Grossmann

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Machine Learning · Computer Science 2025-05-21 Yongxin Deng , Xihe Qiu , Jue Chen , Xiaoyu Tan

We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC)…

Machine Learning · Computer Science 2021-04-16 Minghuan Liu , Tairan He , Minkai Xu , Weinan Zhang

Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to…

Machine Learning · Computer Science 2018-11-06 Adrien Laversanne-Finot , Alexandre Péré , Pierre-Yves Oudeyer

Optimistic exploration is central to improving sample efficiency in reinforcement learning with human feedback, yet existing exploratory bonus methods to incentivize exploration often fail to realize optimism. We provide a theoretical…

Machine Learning · Computer Science 2026-02-18 Wendi Li , Changdae Oh , Sharon Li

Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a…

While large language models (LLMs) have demonstrated impressive performance in question-answering tasks, their performance is limited when the questions require knowledge that is not included in the model's training data and can only be…

Computation and Language · Computer Science 2023-09-22 Abhigya Sodani , Lauren Moos , Matthew Mirman

LLM-based agents have seen promising advances, yet they are still limited in "hard-exploration" tasks requiring learning new knowledge through exploration. We present GLoW, a novel approach leveraging dual-scale world models, maintaining a…

Computation and Language · Computer Science 2025-10-01 Minsoo Kim , Seung-won Hwang

Exploration in environments with sparse rewards remains a fundamental challenge in reinforcement learning (RL). Existing approaches such as curriculum learning and Go-Explore often rely on hand-crafted heuristics, while curiosity-driven…

Machine Learning · Computer Science 2026-02-03 Georgios Sotirchos , Zlatan Ajanović , Jens Kober

Exploration efficiency poses a significant challenge in goal-conditioned reinforcement learning (GCRL) tasks, particularly those with long horizons and sparse rewards. A primary limitation to exploration efficiency is the agent's inability…

Machine Learning · Computer Science 2024-04-22 Lisheng Wu , Ke Chen

Model-based Reinforcement Learning (RL) is a popular learning paradigm due to its potential sample efficiency compared to model-free RL. However, existing empirical model-based RL approaches lack the ability to explore. This work studies a…

Machine Learning · Computer Science 2021-07-16 Yuda Song , Wen Sun