Evaluating Q-Learning Policies for Multi-objective Foraging Task in a Multi-agent Environment.
Mohan YogeswaranS. G. PonnambalamPublished in: ICIRA (2) (2010)
Keyphrases
- multi agent environment
- multi objective
- multi agent
- optimal policy
- single agent
- multi agent systems
- evolutionary algorithm
- multi objective optimization
- reinforcement learning
- optimization algorithm
- state space
- particle swarm optimization
- multiobjective optimization
- cooperative
- multiple objectives
- genetic algorithm
- dynamic environments
- function approximation
- nsga ii
- multi objective optimization problems
- objective function
- learning algorithm
- multiple agents
- decision problems
- hierarchical reinforcement learning
- conflicting objectives
- reward function
- swarm intelligence
- ant colony optimization
- reinforcement learning algorithms
- action selection
- partially observable markov decision processes
- dynamic programming
- foraging theory
- policy iteration
- machine learning
- optimization problems