Generalizing Skills with Semi-Supervised Reinforcement Learning.
Chelsea FinnTianhe YuJustin FuPieter AbbeelSergey LevinePublished in: CoRR (2016)
Keyphrases
- semi supervised
- reinforcement learning
- supervised learning
- semi supervised learning
- labeled data
- multi view
- function approximation
- unsupervised learning
- active learning
- learning algorithm
- unlabeled data
- markov decision processes
- robotic control
- temporal difference learning
- model free
- machine learning
- state space
- labeled examples
- transfer learning
- semi supervised classification
- batch mode
- multi agent reinforcement learning
- learning process
- temporal difference
- label propagation
- pairwise constraints
- neural network
- information literacy
- function approximators
- lifelong learning
- co training
- learning problems
- optimal policy