Self-Paced Contextual Reinforcement Learning.
Pascal KlinkHany AbdulsamadBoris BelousovJan PetersPublished in: CoRL (2019)
Keyphrases
- reinforcement learning
- contextual information
- function approximation
- state space
- context sensitive
- learning algorithm
- learning process
- model free
- context dependent
- temporal difference learning
- dynamic programming
- reinforcement learning algorithms
- markov decision processes
- robotic control
- neural network
- optimal control
- transfer learning
- evaluation function
- learning problems
- online course
- optimal policy
- temporal difference
- context aware
- objective function
- stochastic approximation
- policy gradient
- case study