Multi-Agent Machine Learning

Index

• Autoregressive exogenous (ARX) model
• Bellman equation
• Bellman optimality equation see optimal state-value function
• Channel equalization
• Co-fields technique
• Defuzzification method
• Differential games (DGs)
  • definition
  • evader–pursuer game
    • capture radius
    • capture time
    • control strategy
    • eligibility traces
    • equations of motion
    • learns to escape
    • membership functions
    • pursuer evader dynamics
  • fuzzy systems see fuzzy inference systems (FISs)
  • guarding a territory game see guarding a territory game
  • homicidal chauffeur
    • capture time
    • maximum steering angle
    • minimum turning radius
    • problem model
    • pursuer's vs. evader's speed
    • simulation results
  • reinforcement learning algorithms
• Dirty gradient method
• Dynamic programming
• Echo cancellation
• Evader–pursuer game
  • capture radius
  • capture time
  • control strategy
  • eligibility traces
  • equations of motion
  • learns to escape
  • membership functions
• Exponential moving-average Q-learning (EMA Q-learning) algorithm
• Finite impulse response (FIR) filter
• Friend-or-foe Q-learning (FFQ) algorithm
• Fuzzification method
• Fuzzy actor–critic learning (FACL) algorithm
• Fuzzy inference systems (FISs)
  • actor–critic learning system
    • algorithm
    • architecture
    • definition
    • exploration part
    • prediction error
    • random white noise
    • value function
  • controller structure
  • fuzzifier and defuzzifier
  • fuzzy sets and rules
    • crisp/classical set
    • IF-THEN rules
    • linguistic labels, MFs
    • union and intersection operations
  • product inference engine
    • definition
    • generalized modus ponens
    • intersection and union ...