Learning Goal-Conditioned Representations for Language Reward Models.
Vaskar NathDylan SlackJeff DaYuntao MaHugh ZhangSpencer WhiteheadSean HendryxPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- learning process
- learning systems
- learning algorithm
- prior knowledge
- learning models
- supervised learning
- e learning
- qualitative models
- language learning
- learning tasks
- mobile learning
- accurate models
- online learning
- natural language
- feature representations
- multiple representations
- distributed representations
- learned models
- pattern languages
- complex systems
- unsupervised learning
- programming language
- dynamic programming