Interpretable Reinforcement Learning with Multilevel Subgoal Discovery.
Alexander V. DeminDenis K. PonomaryovPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- knowledge discovery
- reinforcement learning algorithms
- learning algorithm
- data sets
- discovery process
- goal oriented
- model free
- partial order
- optimal policy
- learning process
- markov decision processes
- state space
- pattern discovery
- machine learning
- robotic control
- transition model
- multi agent reinforcement learning
- scientific discovery
- control policy
- control problems
- real time
- databases
- data mining
- optimal control
- multi agent
- association rules