Multi-agent Collaboration for Feasible Collaborative Behavior Construction and Evaluation
This addresses the challenge of efficient collaboration in high-dynamics, multi-agent environments like robotics, though it is incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of long computation time and unsafe policy exploration in multi-agent collaboration by proposing a method to construct a feasible collaborative behavior set using action space discretization and model-based prediction, then selecting optimal behaviors via deep Q-learning, achieving efficient and accurate calculation as verified in RoboCup Small Size League robots.
In the case of the two-person zero-sum stochastic game with a central controller, this paper proposes a best collaborative behavior search and selection algorithm based on reinforcement learning, in response to how to choose the best collaborative object and action for the central controller. In view of the existing multi-agent collaboration and confrontation reinforcement learning methods, the methods of traversing all actions in a certain state leads to the problem of long calculation time and unsafe policy exploration. This paper proposes to construct a feasible collaborative behavior set by using action space discretization, establishing models of both sides, model-based prediction and parallel search. Then, we use the deep q-learning method in reinforcement learning to train the scoring function to select the optimal collaboration behavior from the feasible collaborative behavior set. This method enables efficient and accurate calculation in an environment with strong confrontation, high dynamics and a large number of agents, which is verified by the RoboCup Small Size League robots passing collaboration.