Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills.
Hongcai HeAnjie ZhuShuang LiangFeiyu ChenJie ShaoPublished in: AAAI (2024)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- input output
- learning algorithm
- meta level
- reinforcement learning algorithms
- state space
- machine learning
- knowledge domains
- policy search
- model free
- gaussian mixture
- optimal policy
- maximum likelihood
- supervised learning
- learning process
- gaussian noise
- mobile robot
- lifelong learning
- neural network
- meta reasoning
- transfer learning
- learning problems
- evaluation function
- optimal control
- probabilistic model
- temporal difference
- information technology