Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning.
Shakir MohamedDanilo Jimenez RezendePublished in: NIPS (2015)
Keyphrases
- reinforcement learning
- information sources
- information retrieval
- information content
- search engine
- structural information
- information sharing
- end users
- contextual information
- state space
- temporal difference
- optimal policy
- higher level
- information extraction
- database
- domain knowledge
- optical flow
- genetic algorithm
- real time