In this paper, we investigate the problem of air-to-air drone interception for counter-UAS operations, using multi-agent reinforcement learning and strategic surrounding approaches. These intruding drones are modeled by Boid Algorithm, analogous to flocks of birds. The fleet of interceptors (agents) are assigned to intercept or chase the intruders (targets) mid air at designated area. We separated the problem into two types: 1) swarm for herding or chasing and 2) swarm for intercepting or catching. The difference is the end of the operations, whether the agents need to hit the target. For herding or chasing purposes we employed CROWS algorithm for herding. We also applied Multi-agent reinforcement to strategically positions the agents at specific positions to create surrounding arc formation for herding. For intercepting or catching purpose, we applied the StringNet strategy to break, herd and encircle several subgroups of targets. For both purposes, there is requirement for task allocation algorithm to assign each of the agent to track and look for specific target within the subgroup, for better chasing (intervention) effectiveness and better use of resources, especially in cases of heterogeneous (non-identical) chasing agents. The heuristic task allocation framework is modeled as matching and optimization problem and based on the weapon target assignment problem. The preliminary mix-integer, non-linear problem (MINLP) formulations are based on probability of interception, resource readiness and threat evaluation are used. Preliminary works have shown that the combination of the proposed Hunting, StringNet and heuristic task allocation work for as many as 40+ targets, and by a much lessor (20+) chasers for both interception and herding.