Argumentation Accelerated Reinforcement Learning for RoboCup Keepaway-Takeaway.
Yang GaoFrancesca ToniPublished in: TAFA (2013)
Keyphrases
- robocup soccer
- reinforcement learning
- multi agent
- temporal difference
- robotic soccer
- function approximation
- state space
- agent communication
- reinforcement learning algorithms
- dynamic programming
- markov decision processes
- evidential reasoning
- argumentation systems
- argumentation skills
- argumentation semantics
- model free
- defeasible reasoning
- machine learning
- learning problems
- transfer learning
- policy iteration
- markov decision process
- monte carlo
- optimal policy
- td learning
- supervised learning
- learning algorithm