Reward inference of discrete-time expert's controllers: A complementary learning approach.
Adolfo PerrusquíaWeisi GuoPublished in: Inf. Sci. (2023)
Keyphrases
- reinforcement learning
- learning process
- inverse reinforcement learning
- learning algorithm
- knowledge acquisition
- online learning
- bayesian networks
- learning problems
- structured prediction
- neural network
- state space
- markov chain
- belief networks
- relational learning
- reward function
- learning capabilities
- parameter learning
- efficient learning
- inference process