An Approach of Temporal Difference Learning Using Agent-Oriented Programming.
Amelia BadicaCostin BadicaMirjana IvanovicDejan MitrovicPublished in: CSCS (2015)
Keyphrases
- temporal difference learning
- agent oriented programming
- fixed point
- multi agent systems
- function approximation
- rapid prototyping
- evaluation function
- temporal difference
- approximate value iteration
- reinforcement learning
- game playing
- ontology reasoning
- markov decision process
- reinforcement learning algorithms
- monte carlo
- state space
- multi agent
- radial basis function
- description logics
- function approximators
- machine learning