Proximity-Based Reward Systems for Multi-Agent Reinforcement Learning
Bibliographic record
Abstract
Unmanned vehicles, such as drones, have surged in popularity in recent years. Swarms of these vehicles offer new opportunities in applications such as agriculture, weather monitoring and natural events management. However, efficiently controlling a large swarm of unmanned vehicles poses a significant challenge. Intelligent solutions, particularly reinforcement learning, have been proposed to address this challenge. We introduce a proximity-based reward system for multi-agent reinforcement learning to handle the issue of reward sparsity. Our goal is to develop an approach for controlling a swarm towards a common objective while maintaining robust swarm cohesion. In this paper, we compare various distance-based functions to build a comprehensive reward system. Specifically, we explore the Euclidean, Manhattan, Chebyshev and Minkowski distances in our experiments. We evaluate the impact of these proximity-based reward systems on four reinforcement learning algorithms. We conduct a comparison of our reward systems using various metrics during validation and test episodes. Our goal is to highlight the importance of comparing different algorithms and distance functions in the development of multiagent reinforcement learning systems.
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 | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".