Reinforcement learning with particles for instant optimality.
Tsuyoshi BeppuAkira NotsuKatsuhiro HondaHidetomo IchihashiPublished in: SCIS&ISIS (2012)
Keyphrases
- reinforcement learning
- function approximation
- model free
- temporal difference
- particle swarm
- markov decision processes
- temporal difference learning
- dynamic programming
- state space
- optimal policy
- transfer learning
- average reward
- machine learning
- optimal solution
- multi agent
- swarm optimization
- densely packed
- artificial neural networks
- search algorithm
- robot control
- markov decision process
- learning problems
- learning process
- reinforcement learning methods
- robotic control