What can I do here? A Theory of Affordances in Reinforcement Learning.
Khimya KhetarpalZafarali AhmedGheorghe ComaniciDavid AbelDoina PrecupPublished in: ICML (2020)
Keyphrases
- reinforcement learning
- machine learning
- function approximation
- real time
- data sets
- formal theory
- general theory
- theoretical basis
- information theory
- markov decision processes
- state space
- dynamic programming
- supervised learning
- optimal control
- computer vision
- reinforcement learning algorithms
- learning algorithm
- information retrieval