Curiosity-driven exploration in sparse-reward multi-agent reinforcement learning

J Li, P Gajane - arxiv preprint arxiv:2302.10825, 2023 - arxiv.org
Sparsity of rewards while applying a deep reinforcement learning method negatively affects
its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via …

Subgoal-based Hierarchical Reinforcement Learning for Multi-Agent Collaboration

C Xu, C Zhang, Y Shi, R Wang, S Duan, Y Wan… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advancements in reinforcement learning have made significant impacts across
various domains, yet they often struggle in complex multi-agent environments due to issues …

Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation

A Andres, E Villar-Rodriguez… - 2022 IEEE Symposium …, 2022 - ieeexplore.ieee.org
Reinforcement Learning has emerged as a strong alternative to solve optimization tasks
efficiently. The use of these algorithms highly depends on the feedback signals provided by …

Words as Beacons: Guiding RL Agents with High-Level Language Prompts

U Ruiz-Gonzalez, A Andres, PG Bascoy… - arxiv preprint arxiv …, 2024 - arxiv.org
Sparse reward environments in reinforcement learning (RL) pose significant challenges for
exploration, often leading to inefficient or incomplete learning processes. To tackle this …

The impact of intrinsic rewards on exploration in Reinforcement Learning

A Kayal, E Pignatelli, L Toni - arxiv preprint arxiv:2501.11533, 2025 - arxiv.org
One of the open challenges in Reinforcement Learning is the hard exploration problem in
sparse reward environments. Various types of intrinsic rewards have been proposed to …

Advancing towards Safe Reinforcement Learning over Sparse Environments with Out-of-Distribution Observations: Detection and Adaptation Strategies

A Martinez-Seras, A Andres… - 2024 International Joint …, 2024 - ieeexplore.ieee.org
Safety in AI-based systems is among the highest research priorities, particularly when such
systems are deployed in real-world scenarios subject to uncertainties and unpredictable …

Episodic Novelty Through Temporal Distance

Y Jiang, Q Liu, Y Yang, X Ma, D Zhong, H Hu… - arxiv preprint arxiv …, 2025 - arxiv.org
Exploration in sparse reward environments remains a significant challenge in reinforcement
learning, particularly in Contextual Markov Decision Processes (CMDPs), where …

Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models

A Andres, J Del Ser - arxiv preprint arxiv:2410.07404, 2024 - arxiv.org
Exploration remains a significant challenge in reinforcement learning, especially in
environments where extrinsic rewards are sparse or non-existent. The recent rise of …

Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards

A Andres, D Zha, J Del Ser - 2023 IEEE Symposium Series on …, 2023 - ieeexplore.ieee.org
Exploration poses a fundamental challenge in Reinforcement Learning (RL) with sparse
rewards, limiting an agent's ability to learn optimal decision-making due to a lack of …

Reward Specifications in Collaborative Multi-agent Learning: A Comparative Study

M Hasan, R Niyogi - Proceedings of the 39th ACM/SIGAPP Symposium …, 2024 - dl.acm.org
Reinforcement learning is a prominent learning paradigm that seeks to maximize cumulative
rewards over time. Nevertheless, some real-life problems often exhibit inherent sparsity in …