Multi-agent Deep Reinforcement Learning With Human Strategies

Abstract

Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In this paper, we introduce an approach that integrates human strategies to increase the exploration capacity of multiple deep reinforcement learning agents. We also report the development of our own multi-agent environment called Multiple Tank Defence to simulate the proposed approach. The results show the significant performance improvement of multiple agents that have learned cooperatively with human strategies. This implies that there is a critical need for human intellect teamed with machines to solve complex problems. In addition, the success of this simulation indicates that our multi-agent environment can be used as a testbed platform to develop and validate other multi-agent control algorithms.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keynguyen2018multi

Related papers

• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• A Further Exploration Of Deep Multi-agent Reinforcement Learning With Hybrid Action Space (2022)5.84
• Deep Reinforcement Learning For Multi-agent Systems: A Review Of Challenges, Solutions And Applications (2018)22.57
• Deep Reinforcement Learning For Multi-agent Interaction (2022)9.23
• Hierarchical Multi-agent Reinforcement Learning For Air Combat Maneuvering (2023)8.82
• Collaborating With Humans Without Human Data (2021)0.00
• Distributed Deep Reinforcement Learning: A Survey And A Multi-player Multi-agent Learning Toolbox (2022)11.39