Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning.
Elie AljalboutMaximilian UlmerRudolph TriebelPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- mid level
- data driven
- function approximation
- low level
- reinforcement learning algorithms
- multiple representations
- machine learning
- visual patterns
- model free
- visual features
- state space
- dynamic programming
- visual information
- higher level
- learning problems
- visual data
- visual search
- supervised learning
- object recognition
- action space
- visual processing
- multi agent