Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems.
Mohammad KachueeSungjin LeePublished in: CoRR (2022)
Keyphrases
- ai systems
- artificial intelligence
- intelligent systems
- multi modal
- concave convex procedure
- natural language generation
- optimization method
- information extraction
- computational intelligence
- optimization problems
- evolutionary algorithm
- case study
- learning styles
- optimization algorithm
- optimal policy
- lagrange multipliers
- machine learning
- real time