Self-Paced Contextual Reinforcement Learning.
Pascal KlinkHany AbdulsamadBoris BelousovJan PetersPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- contextual information
- context sensitive
- optimal policy
- state space
- learning algorithm
- model free
- markov decision processes
- reinforcement learning algorithms
- temporal difference learning
- machine learning
- control problems
- multi agent
- least squares
- temporal difference
- learning problems
- context dependent
- brain computer interface
- transition model
- robotic control
- direct policy search
- transfer learning
- database
- dynamic programming
- learning process
- case study
- image processing
- neural network
- data sets