Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning.
Michiel van der MeerMatteo PirottaElia BruniPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- language learning
- programming language
- computer programs
- function approximation
- natural language
- state space
- machine learning
- learning process
- multi agent
- optimal policy
- knowledge base
- learning algorithm
- learning classifier systems
- neural network
- reinforcement learning algorithms
- computational linguistics
- specification language
- operational semantics