Safe Finite-Time Reinforcement Learning for Pursuit-Evasion Games.
Nick-Marios T. KokolakisKyriakos G. VamvoudakisPublished in: CDC (2022)
Keyphrases
- pursuit evasion
- reinforcement learning
- action sets
- state and action spaces
- learning agents
- markov decision processes
- function approximation
- multiagent learning
- reinforcement learning agents
- video games
- game theory
- game design
- finite number
- game theoretic
- computer games
- temporal difference
- action space
- machine learning
- reinforcement learning algorithms
- perfect information
- game playing
- state space
- learning process
- multi agent
- learning algorithm
- model free
- stochastic games
- markov decision problems
- monte carlo tree search
- two player games
- imperfect information
- finite automata
- educational games
- nash equilibrium
- dynamic programming
- temporal difference learning
- nash equilibria
- partially observable
- learning classifier systems
- multi agent reinforcement learning
- optimal control
- transfer learning
- resource allocation
- robotic control
- games played