arXiv cs.AI· Junhao Cao, Tao Wang, Zipeng Xie, Hongyi Xia, Jianian Wu, Lixia Huang·· 4 小时前AI 评分20
CoverShare:用互补路线学习柿园新梢生长期巡检
Learning Complementary Routes for Scouting Persimmon Orchards during Shoot Growth with CoverShare
AI 导读
CoverShare 在固定动作预算下学习互补巡检路线,按“去掉某策略后损失的状态覆盖”和访问该状态的策略数量重新分配辅助奖励,同时保持池化熵目标与辅助奖励总量不变。
正文 · 原文
Abstract:At the study orchard, scouting during persimmon shoot growth focuses on leaf color change, leaf area, and internode length. Several routes may share an access lane, yet each can offer a view of row segments that the others miss. We introduce CoverShare to learn complementary routes under a fixed action budget. Within Policy Gradient for Parallel State Entropy maximization (PGPSE), CoverShare redistributes auxiliary rewards according to the state coverage lost when each policy is omitted and the number of policies visiting each state. It preserves the pooled entropy objective and total auxiliary reward. We simulated the annotated road network of a 6.7-ha site with 107 observable persimmon scouting units across five zones. At 40 actions per route, six distinct policies covered an expected 17.84 units perinspection, compared with 8.28 for six independent runs of one policy, averaged across eight training seeds. With the same policies trained on 40-action routes, extending each inspection route to 80 and 120 actions raised coverage to 22.52 and 28.38 units. Across seven public discrete-state tasks, CoverShare increased state support by a mean of 16.29% over the team-entropy baseline. Controlled ablations identified leave-one-policy-out coverage as the main contributor to these gains.
| Comments: | Following collaboration with NUDT and NUIST, Tao Wang and Zipeng Xie substantially advanced the agricultural application. Lixia Huang secured additional funding. Xiaopeng Yi and Ping Guo withdrew due to heavy teaching commitments. All authors, including those added and removed, agreed to the revised author list and order, with Lixia Huang as corresponding author |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.27507 [cs.LG] |
| (or arXiv:2608.27507v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2608.27507 arXiv-issued DOI via DataCite |
Submission history
From: Junhao Cao [view email]
[v1]
Thu, 27 Aug 2026 06:24:03 UTC (2,044 KB)
[v2]
Tue, 17 Nov 2026 17:20:21 UTC (9,476 KB)
来源:arXiv cs.AI · arxiv.org