MétaCan
Menu
Back to cohort
Record W4411517337 · doi:10.22399/ijcesen.2483

Optimizing Hybrid AI Models with Reinforcement Learning for Complex Problem Solving

2025· article· en· W4411517337 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueInternational Journal of Computational and Experimental Science and Engineering · 2025
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Technologies in Various Fields
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsReinforcement learningArtificial intelligenceComputer scienceMachine learningDeep learningTask (project management)AdaptabilityProcess (computing)Engineering

Abstract

fetched live from OpenAlex

Hybrid AI models have gained significant attention due to their ability to combine the strengths of multiple artificial intelligence techniques, such as deep learning, evolutionary algorithms, and reinforcement learning (RL), to solve complex, real-world problems. This research explores the optimization of hybrid AI models with reinforcement learning to enhance their problem-solving capabilities in diverse domains, including robotics, healthcare, and autonomous systems. The proposed methodology integrates deep reinforcement learning (DRL) with genetic algorithms (GA) and neural networks to create adaptive models capable of learning from both supervised data and interactive environments. Through this integration, the hybrid models can optimize their decision-making processes over time, balancing exploration and exploitation to maximize performance. The optimization process involves tuning the parameters of the reinforcement learning agent, such as the learning rate, discount factor, and exploration-exploitation ratio, to achieve the best possible outcome. Experimental results demonstrate that the hybrid AI model outperforms traditional single-algorithm approaches in terms of efficiency and accuracy. Specifically, in a robotic task optimization problem, the hybrid model achieved a 25% improvement in task completion time compared to standalone deep learning models. In a healthcare diagnosis scenario, the hybrid model showed a 15% increase in diagnostic accuracy, significantly reducing false positives and negatives. Furthermore, the optimization led to a 30% reduction in the training time compared to models that did not incorporate reinforcement learning. The findings indicate that combining reinforcement learning with other AI techniques can significantly enhance the adaptability, efficiency, and problem-solving abilities of AI models. This research provides a foundation for developing more sophisticated hybrid AI systems for complex, dynamic environments.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.636
Threshold uncertainty score0.274

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.011
GPT teacher head0.271
Teacher spread0.260 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it