Adversary agent reinforcement learning for pursuit-evasion

Huang, Xun

doi:10.48550/arxiv.2108.11010

Cited by 1 publication

(2 citation statements)

References 21 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…∅m , i = ∅ m , i x i , mi . t (20) ∅u , i = ∅ u , i x i , mi . t (21) ĤWJ = H WJ x i , ∂ x ∅J , i x i , mi .…”

Section: Homogeneous Decentralised Actor-critic-mass Algorithmunclassified

See 1 more Smart Citation

Cooperative control for multi-player pursuit-evasion games embedded on communication technology with reinforcement learning

kavin,

Kamala

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent advances in research on the Multi-agent System (MAS) optimal control issue will help sectors like robotics, communications, and power systems. This work looks at the intelligent design of a large-scale multi-pursuer and multi-evader pursuit-evasion game. Based on reinforcement learning, a distributed cooperative pursuit method with communication is created. The famed Curse of Dimensionality poses a serious danger to multi-player pursuit-evasion game designs due to the sheer number of agents, especially in hostile areas where there aren't many communication options available to encourage player information exchange. In order to find the best pursuit-evasion strategies using a novel type of probability density function (PDF) rather than exhaustive data from all the remaining teams or agents, the Mean Field Games (MFG) theory has been used. A novel MAS optimum type oversight system with a decentralised and computer-friendly decision method is urgently needed. Mean field game theory is used to create the Actor-critic-mass (ACM), a decentralised optimal control system, to address the aforementioned issues. Additionally, the homogeneous decentralised Actor-critic-mass (HDACM) which improves the ACM method, does away with restrictions like homogeneous agents and cost functions. Finally, two applications make use of the PAS algorithm.

show abstract

“…∅m , i = ∅ m , i x i , mi . t (20) ∅u , i = ∅ u , i x i , mi . t (21) ĤWJ = H WJ x i , ∂ x ∅J , i x i , mi .…”

Section: Homogeneous Decentralised Actor-critic-mass Algorithmunclassified

“…Another type of chase-evasion game involves the pursuit and evasion of players in a de ned setting, such as a grid map. With the advent of Mean Field Games theory, Parsons developed this novel strategy in [20,21,22]. Numerous outcomes and applications of the chase evasion game have been suggested based on these two fundamental works.…”

Section: Introductionmentioning

confidence: 99%

Cooperative control for multi-player pursuit-evasion games embedded on communication technology with reinforcement learning

kavin,

Kamala

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Adversary agent reinforcement learning for pursuit-evasion

Cited by 1 publication

References 21 publications

Cooperative control for multi-player pursuit-evasion games embedded on communication technology with reinforcement learning

Cooperative control for multi-player pursuit-evasion games embedded on communication technology with reinforcement learning

Contact Info

Product

Resources

About