First-Order Problem Solving through Neural MCTS based Reinforcement Learning.
Ruiyang XuPrashank KadamKarl J. LieberherrPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- fitted q iteration
- network architecture
- function approximation
- monte carlo tree search
- first order logic
- neural network
- higher order
- model free
- explanation based learning
- markov decision processes
- case based reasoning
- reinforcement learning algorithms
- learned knowledge
- artificial intelligence
- monte carlo
- complex problem solving
- temporal difference
- information processing
- optimal policy
- dynamic programming
- reinforcement learning methods
- multi agent
- neural model
- learning algorithm
- neural fuzzy
- engineering design
- solving problems
- bio inspired
- biologically inspired
- knowledge acquisition
- learning process
- machine learning
- learning rules
- control problems
- temporal difference learning
- associative memory
- supervised learning
- robotic control