Symbolic computation in RL/1.
Sieger van DenneheuvelKaren L. KwastPeter van Emde BoasFred de GeusErnest RotterdamPublished in: DEXA (1991)
Keyphrases
- reinforcement learning
- imperative programs
- autonomous learning
- automated deduction
- action selection
- function approximation
- multi agent
- learning classifier systems
- model free
- reinforcement learning algorithms
- neural network
- state space
- markov decision processes
- action space
- partially observable domains
- learning process
- website
- temporal difference learning
- artificial intelligence
- machine learning
- data mining