Reinforcement Learning for Unified Allocation and Patrolling in Signaling Games with Uncertainty.
Aravind VenugopalElizabeth BondiHarshavardhan KamarthiKeval DholakiaBalaraman RavindranMilind TambePublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- multi agent
- leader follower
- action sets
- learning agents
- function approximation
- learning algorithm
- resource allocation
- multiagent learning
- computer games
- video games
- reinforcement learning agents
- markov decision processes
- dynamic allocation
- partial observability
- resource constrained
- reinforcement learning algorithms
- realistic settings
- machine learning
- nash equilibria
- information gathering
- model free
- game playing
- game design
- optimal control
- uncertain data
- multiagent systems
- learning process
- decision theory
- single agent
- game play
- optimal allocation
- nash equilibrium
- allocation strategy
- incomplete information
- game theory
- dynamic programming