Generative reinforcement learning for self-sustainable STAR-RIS assisted UAV communications
Bibliographic record
Abstract
This paper investigates the communication performance optimization of a Simultaneous Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS) assisted Unmanned Aerial Vehicle (UAV) network, with particular attention to the power consumption constraints of practical STAR-RIS hardware. The objective is to maximize achievable sum rate of all users by jointly optimizing the UAV trajectory, beamforming, STAR-RIS coefficients, and energy harvesting slot allocation. Due to the non-convex and highly coupled nature of the aforementioned joint optimization problem, this paper proposes an efficient Generative Adversarial Network Twin Delayed Deep Deterministic policy gradient (GAN-TD3) algorithm. The GAN-TD3 algorithm uses the adversarial learning mechanism of generative adversarial networks to approximate the distribution of action values. The generator network estimates action value, the target generator network outputs target action value, and the discriminator network minimizes the difference between action value and target action value calculated by the Bellman calculation formula. This approach mitigates the impact of random fluctuations in action value estimation, thus improving learning stability. Numerical results demonstrate that the proposed GAN-TD3 algorithm outperforms the baseline algorithms in terms of convergence stability and significantly improves the system rate.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".