Cooperative-Search
Multi-agent RL algorithms are applied to large-scale cooperative target searching mission.
Y. Sun, Z. Wu, Q. Zhang, Z. Shi and Y. Zhong, "Multi-Agent Reinforcement Learning for Distributed Cooperative Targets Search," 2021 IEEE International Conference on Unmanned Systems (ICUS), Beijing, China, 2021, pp. 711-716, doi: 10.1109/ICUS52573.2021.9641124.
Env:
- flight_easy: Continuous search environment
- flight: Add probability graph to flight_easy
- search_env: Discrete search environment
- simple_spread: A test env
Algorithm:
- QMIX
- DOP
- VDN
- Reinforce
Result:
env = flight_easy target_num = 15
- agent_num = 1, agent_mode = 0:
- agent_num = 3, agent_mode = 0:
- agent_num = 5, agent_mode = 0:
...