Guided Experience Prioritization for Continuous Reinforcement Learning
Open Access
- 16 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 180145-180155
Abstract
A primary limiting factor in modern deep learning is the availability of computational resources, a constraint that becomes particularly pronounced in the context of complex reinforcement learning tasks. Hardware performance limitations often result in prolonged training procedures, which are frequently correlated with increased operational costs. In many cases, these limitations place such solutions at a disadvantage, which is why cost reduction remains one of the main priorities. In the field of deep reinforcement learning, a commonly employed method for this purpose is the guided selection of training samples, which emphasizes the most informative state transitions, thereby allowing the agent to maximize its learning from the most critical experiences. However, similarly to the decision-making process, it is also crucial to ensure that the agent has information about which samples are important. Therefore, exploration must be incorporated in this context as well, enabling the agent to acquire the most diverse possible knowledge regarding both the samples themselves and their informational value. The paper introduces a sampling method for continuous-output reinforcement learning agents, which balances, in a problem-independent manner, the necessary exploration and the selection of the most informative samples that enhance learning speed. Due to the presented Upper Confidence Bound-based sampling, both exploration and exploitation are ensured simultaneously, and by tuning their balance appropriately, training can be accelerated. This approach improves the efficiency of the training process, which often constitutes the primary bottleneck.Keywords
Funding Information
- European Union within the framework of the National Laboratory for Autonomous Systems (RRF-2.3.1-21-2022-00002)
- Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, through the TKP2021 Funding Scheme (BME-NVA-02)
- Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund, through the EKÖP-24-2-BME-46 Funding Scheme (2024-2.1.1-EKÖP-2024-00003)
This publication has 20 references indexed in Scilit:
- Distributed Highway Control: A Cooperative Reinforcement Learning-Based ApproachIEEE Access, 2024
- Prioritized experience replay based on dynamics priorityScientific Reports, 2024
- Enhanced Experience Prioritization: A Novel Upper Confidence Bound ApproachIEEE Access, 2023
- Large language models in medicineNature Medicine, 2023
- Quo vadis artificial intelligence?Discover Artificial Intelligence, 2022
- Hyperparameter Optimization2019
- Human-level control through deep reinforcement learningNature, 2015
- Decision Trees2006
- Reinforcement Learning1997
- Artificial intelligence: A modern approachArtificial Intelligence, 1996