TD(λ) and Q-learning based Ludo players.
Majed AlhajryFaisal AlviMoataz A. AhmedPublished in: CIG (2012)
Keyphrases
- td learning
- reinforcement learning algorithms
- reinforcement learning
- temporal difference learning
- temporal difference
- function approximation
- eligibility traces
- learning algorithm
- evaluation function
- model free
- temporal difference methods
- cooperative
- game play
- state space
- game theory
- game playing
- markov decision processes
- reinforcement learning methods
- reinforcement learning problems
- action selection
- policy iteration
- fixed point
- policy evaluation
- learning rate
- td methods
- soccer games
- multi agent reinforcement learning
- dynamic programming
- repeated games
- markov decision process
- online game