Transfer deep reinforcement learning for accelerated task scheduling in cognitive radar
Bibliographic record
Abstract
Cognitive radars adapt to their environment by continuously sensing, interacting with, and learning from the environment. This paradigm can be applied to a multifunction radar (MFR), which performs multiple functions such as surveillance, tracking, and communications. A radar resource management (RRM) module assigns the necessary resources to these functions according to their priority. While assigning the time resource, RRM becomes especially challenging as: 1) some of the functions (tasks) need to be delayed or even dropped in overload situations, 2) task distributions may change with a changing environment. In this paper, we propose the use of transfer learning (TL) in deep reinforcement learning (DRL) as an effective solution. Our DRL approach is based on Monte Carlo Tree Search (MCTS) aided by a deep neural network (DNN). DNN-based MCTS is slow as it learns from scratch, thereby demanding a large number of rollouts in its search. In changing environments, we investigate how to reduce computational burden using TL. In particular, we tackle the challenge of slow convergence by transferring the policy learned by a DRL agent for a source task distribution to the new DRL agent at a different target task distribution. Our approach shows a remarkable reduction in convergence time compared with its non-accelerated counterpart when tested against different distributions, thereby resulting in a quick adaptation to new 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.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".