TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning.
Minchao WuMichael NorrishChristian WalderAmir DezfouliPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- deep learning
- supervised learning
- online learning
- markov decision processes
- background knowledge
- autonomous learning
- learning tasks
- learning systems
- learning experience
- function approximation
- partially observable
- prior knowledge
- temporal difference learning
- machine learning