Improving Policy Learning via Language Dynamics Distillation.
Victor ZhongJesse MuLuke ZettlemoyerEdward GrefenstetteTim RocktäschelPublished in: NeurIPS (2022)
Keyphrases
- learning algorithm
- natural language
- learning process
- learning systems
- active learning
- learning problems
- training data
- language acquisition
- programming language
- online learning
- learning scheme
- dynamical systems
- inverse reinforcement learning
- object oriented programming
- learning tasks
- unsupervised learning
- knowledge acquisition
- supervised learning
- bayesian networks