Off-Policy Differentiable Logic Reinforcement Learning.
Li ZhangXin LiMingzhong WangAndong TianPublished in: ECML/PKDD (2) (2021)
Keyphrases
- reinforcement learning
- logic programming
- modal logic
- objective function
- automated reasoning
- multi agent
- function approximation
- model free
- policy search
- reinforcement learning algorithms
- state space
- machine learning
- learning algorithm
- supervised learning
- deontic logic
- predicate logic
- defeasible logic
- logical framework
- multi valued
- dynamic programming
- markov decision processes
- temporal difference
- action selection
- database
- markov decision process
- learning process
- computational properties
- set theory
- least squares
- proof theory
- transition model
- neural network