Multi-agent game AI design method based on attention mechanism and reinforcement learning

A reinforcement learning, multi-agent technology, applied in the field of multi-agent deep reinforcement learning, can solve the problems of increasing complexity of the final strategy fusion process and insufficient strategy fusion, and achieve the effect of improving learning efficiency

CN114130034AActive Publication Date: 2022-03-04TIANJIN UNIV
11 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-03-04

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a multi-agent game AI (artificial intelligence) design method based on an attention mechanism and reinforcement learning, which comprises the following steps: firstly, performing entity-based local information division and grouping on agent original observation information; secondly, obtaining a local strategy at the current moment based on each piece of grouping information representation, obtaining an attention weight corresponding to local information according to the action-observation historical information, and aggregating all the local strategies according to the attention weight to obtain a local information strategy; and finally, aggregating the local information strategy and the original observation information as a reference strategy of strategy input and output to obtain a final strategy of the intelligent agent. Compared with the prior art, the method has the advantages that the problem of agent observation information redundancy in a multi-agent system is solved, and the learning efficiency of the agents can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of multi-agent deep reinforcement learning, in particular to a design method for a multi-agent game AI in a combat environment. Background technique

[0002] Multi-agent reinforcement learning is a very important research field in the field of artificial intelligence. It has been used to solve complex multi-agent problems such as cooperation of a large number of robot systems and automatic driving, and has achieved good results.

[0003] In the field of multi-agent reinforcement learning, most algorithm frameworks adopt the principle of centralized training & distributed execution. Each agent independently uses its own observation information to make decisions during the execution process, thereby alleviating the impact on the policy network caused by the exponential increase in the joint observation space caused by the number of large-scale agents; in the training process, the joint actions of all agents are used- T...

Examples

Embodiment Construction

[0017] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0018] The multi-agent game AI design method based on attention mechanism and reinforcement learning of the present invention includes division of local observation information and fusion of local strategies. like figure 1 Shown is the overall flowchart of the multi-agent game AI design method based on the attention mechanism and reinforcement learning of the present invention. The specific process is as follows:

[0019] Step 1. Divide and group the original observation information of the agent based on entity-based local information, specifically including the following processing:

[0020] Two entity observation features that are similar to entity observation features in the agent's field of view are divided into the same area in the entire field of view to form a group. The entity observation feature is the em...