A reward allocation method for reinforcement learning in stabilizing control tasks.
Shu HosokawaJoji KatoKazushi NakanoPublished in: Artif. Life Robotics (2014)
Keyphrases
- reinforcement learning
- experimental evaluation
- clustering method
- control policy
- significant improvement
- computational cost
- probabilistic model
- cost function
- similarity measure
- pairwise
- high accuracy
- multi agent
- mathematical model
- high precision
- optimal control
- dynamic programming
- robotic systems
- objective function
- transition model