Keyphrases
- reinforcement learning
- markov decision processes
- reward function
- sequential decision making under uncertainty
- visual perception
- finite state
- markov decision process
- dynamical systems
- function approximation
- data sets
- partially observable markov decision processes
- continuous state
- bandit problems
- learning algorithm
- planning problems
- optimal control
- model free
- state space
- dynamic programming
- belief state
- decision making
- fully observable
- long term and short term