Learning a Transferable World Model by Reinforcement Agent in Deterministic Observable Grid-World Environments.
Jurgita Kapociute-DzikieneGailius RaskinisPublished in: Inf. Technol. Control. (2012)
Keyphrases
- world model
- reinforcement learning
- learning algorithm
- learning process
- semantic interpretation
- dynamic environments
- intelligent agents
- multi agent
- learning capabilities
- vision system
- learning tasks
- multi agent environments
- learning agent
- learning mechanism
- decision theoretic
- software agents
- natural language processing
- learning opportunities
- state space
- knowledge representation
- prior knowledge
- decision making