Reinforcement Learning with Success Induced Task Prioritization.
Maria NesterovaAlexey SkrynnikAleksandr PanovPublished in: MICAI (1) (2022)
Keyphrases
- reinforcement learning
- function approximation
- model free
- markov decision processes
- multi agent
- dynamic programming
- state space
- learning algorithm
- multi agent reinforcement learning
- reward function
- learning classifier systems
- user satisfaction
- reinforcement learning algorithms
- control problems
- function approximators
- machine learning
- neural network
- real time
- robotic control
- markov chain
- mobile robot
- hidden markov models
- active learning
- image sequences