We introduce a domain-specific reward mechanism that maximizes yield recovery while minimizing chemical usage by effectively handling noisy infection data and enforcing physical field constraints via action masking. We conduct a rigorous empirical evaluation across diverse, realistic biotic stress scenarios, capturing varying infection distributions and severity levels in row-crop fields. The proposed scheme is evaluated thoroughly, showing the framework's effectiveness and robustness. Experimental results demonstrate that our approach significantly reduces non-target spraying, chemical consumption, and operational costs compared to baseline methods. Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree Mahsa Khosravi a, Zhanhong Jiang b, Joshua R Waite b, Sarah Jones c, Hernan Torres c, Arti Singh c, Baskar Ganapathysubramanian b, Asheesh Kumar Singh c, Soumik Sarkar b a Department of Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, Iowa, USA b Department of Mechanical Engineering, Iowa State University, Ames, Iowa, USA c Department of Agronomy, Iowa State University, Ames, Iowa, USAAbstract This paper presents a novel reinforcement learning (RL)-based planning scheme for optimized robotic management of biotic stresses in precision agriculture.

Proximal policy optimization (PPO) is one of the most popular state-of-the-art on-policy algorithms that has become a standard baseline in modern reinforcement learning with applications in numerous fields. Though it delivers stable performance with theoretical policy improvement guarantees, high variance, and high sample complexity still remain critical challenges in on-policy algorithms. To alleviate these issues, we propose Hybrid-Policy Proximal Policy Optimization (HP3O), which utilizes a trajectory replay buffer to make efficient use of trajectories generated by recent policies. Particularly, the buffer applies the "first in, first out" (FIFO) strategy so as to keep only the recent trajectories to attenuate the data distribution drift. A batch consisting of the trajectory with the best return and other randomly sampled ones from the buffer is used for updating the policy networks. The strategy helps the agent to improve its capability on top of the most recent best performance and in turn reduce variance empirically. We theoretically construct the policy improvement guarantees for the proposed algorithm. HP3O is validated and compared against several baseline algorithms using multiple continuous control environments. Our code is available here.