Privileged Information Dropout in Reinforcement Learning.
Pierre-Alexandre KamiennyKai ArulkumaranFeryal BehbahaniWendelin BoehmerShimon WhitesonPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- privileged information
- function approximation
- model free
- state space
- learning algorithm
- temporal difference
- optimal policy
- histogram intersection kernel
- control problems
- reinforcement learning algorithms
- artificial intelligence
- database
- markov decision processes
- action selection
- temporal difference learning
- machine learning
- transfer learning
- artificial neural networks
- multi agent
- feature selection
- information systems
- real world