Generalizing Skills with Semi-Supervised Reinforcement Learning.
Chelsea FinnTianhe YuJustin FuPieter AbbeelSergey LevinePublished in: ICLR (Poster) (2017)
Keyphrases
- semi supervised
- reinforcement learning
- supervised learning
- semi supervised learning
- semi supervised classification
- pairwise
- function approximation
- unlabeled data
- multi agent
- markov decision processes
- semi supervised clustering
- labeled data
- model free
- pairwise constraints
- unsupervised learning
- optimal control
- multi view
- labeled and unlabeled data
- state space
- temporal difference learning
- learning algorithm
- reinforcement learning algorithms
- communication skills
- robotic control
- machine learning
- co training
- optimal policy
- active learning
- neural network
- high school
- subspace learning
- transfer learning
- text mining
- label propagation
- dynamic programming
- learning process
- multi agent reinforcement learning
- training set
- policy search
- skill development