A topological reinforcement learning agent for navigation.
Arthur Plínio de S. BragaAluizio F. R. AraújoPublished in: Neural Comput. Appl. (2003)
Keyphrases
- learning agent
- reinforcement learning
- state space
- solving problems
- reinforcement learning algorithms
- learning algorithm
- learning capabilities
- function approximation
- markov decision processes
- optimal policy
- learning tasks
- transfer learning
- single agent
- selective perception
- machine learning
- domain specific
- multi agent
- dynamic programming
- action selection
- temporal difference
- domain knowledge
- artificial intelligence