Two-stage training algorithm for AI robot soccer

2021-04-13 · TaeYoung Kim, Luiz Felipe Vecchietti, Kyujin Choi, Sanem Sariel, Dongsoo Har

In multi-agent reinforcement learning, the cooperative learning behavior of agents is very important. In the field of heterogeneous multi-agent reinforcement learning, cooperative behavior among different types of agents in a group is pursued. Learning a joint-action set during centralized training is an attractive way to obtain such cooperative behavior, however, this method brings limited learning performance with heterogeneous agents. To improve the learning performance of heterogeneous agents during centralized training, two-stage heterogeneous centralized training which allows the training of multiple roles of heterogeneous agents is proposed. During training, two training processes are conducted in a series. One of the two stages is to attempt training each agent according to its role, aiming at the maximization of individual role rewards. The other is for training the agents as a whole to make them learn cooperative behaviors while attempting to maximize shared collective rewards, e.g., team rewards. Because these two training processes are conducted in a series in every timestep, agents can learn how to maximize role rewards and team rewards simultaneously. The proposed method is applied to 5 versus 5 AI robot soccer for validation. Simulation results show that the proposed method can train the robots of the robot soccer team effectively, achieving higher role rewards and higher team rewards as compared to other approaches that can be used to solve problems of training cooperative multi-agent.

📄 PDF Abstract BibTeX arXiv:2104.05931

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)Vocal Bursts Valence Prediction

Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework

2026-02-05 · Jipeng Kong, Xinzhe Liu, Yuhang Lin, Jinrui Han 외 arxiv

Soccer presents a significant challenge for humanoid robots, demanding tightly integrated perception-action capabilities for tasks like perception-guided kicking and whole-body balance control. Existing approaches suffer…

Kick-motion Training with DQN in AI Soccer Environment

2022-12-01 · Bumgeun Park, Jihui Lee, TaeYoung Kim, Dongsoo Har

This paper presents a technique to train a robot to perform kick-motion in AI soccer by using reinforcement learning (RL). In RL, an agent interacts with an environment and learns to choose an action in a state at each s…

Reinforcement Learning (RL)

Deep Q-Network for AI Soccer

2022-09-20 · Curie Kim, Yewon Hwang, Jong-Hwan Kim

Reinforcement learning has shown an outstanding performance in the applications of games, particularly in Atari games as well as Go. Based on these successful examples, we attempt to apply one of the well-known reinforce…

Atari Games reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning

2024-05-03 · Dhruva Tirumala, Markus Wulfmeier, Ben Moran, Sandy Huang 외

We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world ro…

Deep Reinforcement Learning Object Tracking reinforcement-learning Reinforcement Learning+1

Efficient Lines Detection for Robot Soccer

2025-07-25 · João G. Melo, João P. Mafaldo, Edna Barros arxiv

Self-localization is essential in robot soccer, where accurate detection of visual field features, such as lines and boundaries, is critical for reliable pose estimation. This paper presents a lightweight and efficient m…

Pose Estimation