Safe Reinforcement Learning with Natural Language Constraints.
Tsung-Yen YangMichael Y. HuYinlam ChowPeter J. RamadgeKarthik NarasimhanPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- natural language
- machine learning
- constraint satisfaction
- question answering
- state space
- multi agent
- natural language processing
- real time
- constraint programming
- function approximation
- constrained optimization
- resource constraints
- language processing
- multi agent reinforcement learning
- natural language interface
- natural language generation
- reinforcement learning algorithms
- model free
- constraint networks
- transfer learning
- artificial intelligence
- search engine