Value-Difference Based Exploration: Adaptive Control between Epsilon-Greedy and Softmax.
Michel TokicGünther PalmPublished in: KI (2011)
Keyphrases
- adaptive control
- nonlinear systems
- control method
- greedy algorithm
- dynamic environments
- feedback control
- control law
- reinforcement learning
- adaptive controller
- variable structure
- search algorithm
- locally optimal
- chaotic systems
- multi modal
- d objects
- convergence speed
- mobile robot
- dynamic programming
- search space
- genetic algorithm
- real time