Conceptual Reinforcement Learning for Language-Conditioned Tasks.
Shaohui PengXing HuRui ZhangJiaming GuoQi YiRuizhi ChenZidong DuLing LiQi GuoYunji ChenPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- natural language
- multiple tasks
- programming language
- conceptual model
- function approximation
- machine learning
- state space
- transfer learning
- data sets
- conceptual models
- language processing
- markov decision processes
- conceptual representation
- action selection
- language learning
- knowledge base
- neural network