Multi-trainer Interactive Reinforcement Learning System.
Zhaori GuoTimothy J. NormanEnrico H. GerdingPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- dynamic programming
- neural network
- user friendly
- virtual reality
- optimal policy
- multi agent
- website
- machine learning
- data analysis
- expert systems
- learning process
- knowledge base
- computer graphics
- markov decision processes
- real world
- real time
- model free
- reinforcement learning algorithms
- policy search
- fitted q iteration