Dynamic Programming for Creating Cooperative Behavior of Two Soccer Robots - Part 1: Computation of State-Action Map.
Ryuichi UedaKohei SakamotoKazutaka TakeshitaTamio AraiPublished in: ICRA (2007)
Keyphrases
- cooperative behavior
- dynamic programming
- evolutionary learning
- state action
- cooperative
- reinforcement learning
- evaluation function
- robot soccer
- mobile robot
- state space
- stochastic games
- evolutionary game theory
- evolutionary algorithm
- optimal control
- markov decision process
- optimal policy
- evolutionary computation
- infinite horizon
- state transitions
- learning process
- artificial neural networks
- multi agent