Keyphrases
- reinforcement learning
- fitted q iteration
- network architecture
- classical logic
- neural network
- modal logic
- function approximation
- bio inspired
- state space
- logic programming
- optimal policy
- transfer learning
- reinforcement learning algorithms
- machine learning
- neural computation
- proof theory
- sensory inputs
- multi agent
- learning process
- dynamic programming
- markov decision processes
- temporal difference
- automated reasoning
- multi valued
- neural model
- genetic algorithm
- predicate logic
- biologically plausible
- supervised learning