A multiagent architecture for concurrent reinforcement learning.
Víctor Uc CetinaPublished in: ESANN (2006)
Keyphrases
- multiagent architecture
- reinforcement learning
- multiagent systems
- hierarchical reinforcement learning
- function approximation
- multi agent
- model free
- markov decision processes
- control problems
- state space
- learning algorithm
- temporal difference
- learning agents
- machine learning
- data sets
- supervised learning
- reinforcement learning algorithms
- stochastic approximation
- concurrent execution
- optimal policy
- database
- dynamic programming
- information retrieval
- state abstraction